Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1268 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 14.5224. Min Range: -14.5224
Max Act: 14.5224. Min Act: -0.1700
Data Index: 7800929 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 14.5224. Min Range: -14.5224
Max Act: 14.4599. Min Act: -0.1700
Data Index: 4249751 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 14.5224. Min Range: -14.5224
Max Act: 14.3974. Min Act: -0.1700
Data Index: 8732315 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 14.5224. Min Range: -14.5224
Max Act: 14.2724. Min Act: -0.1700
Data Index: 504613 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 14.5224. Min Range: -14.5224
Max Act: 14.0849. Min Act: -0.1700
Data Index: 504617 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 14.5224. Min Range: -14.5224
Max Act: 13.9599. Min Act: -0.1700
Data Index: 326987 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 14.5224. Min Range: -14.5224
Max Act: 13.8974. Min Act: -0.1700
Data Index: 8567255 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 14.5224. Min Range: -14.5224
Max Act: 13.9599. Min Act: -0.1700
Data Index: 504607 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 14.5224. Min Range: -14.5224
Max Act: 13.8349. Min Act: -0.1700
Data Index: 3396290 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 14.5224. Min Range: -14.5224
Max Act: 13.8349. Min Act: -0.1700
Data Index: 6685056 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 14.5224. Min Range: -14.5224
Max Act: 13.9599. Min Act: -0.1700
Data Index: 7241632 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 14.5224. Min Range: -14.5224
Max Act: 13.7724. Min Act: -0.1700
Data Index: 3700999 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 14.5224. Min Range: -14.5224
Max Act: 13.7724. Min Act: -0.1700
Data Index: 6257864 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 14.5224. Min Range: -14.5224
Max Act: 13.6474. Min Act: -0.1700
Data Index: 504615 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 14.5224. Min Range: -14.5224
Max Act: 13.6474. Min Act: -0.1700
Data Index: 6088660 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 14.5224. Min Range: -14.5224
Max Act: 13.5849. Min Act: -0.1700
Data Index: 504619 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 14.5224. Min Range: -14.5224
Max Act: 13.6474. Min Act: -0.1700
Data Index: 416838 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 14.5224. Min Range: -14.5224
Max Act: 13.5849. Min Act: -0.1700
Data Index: 8049794 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 14.5224. Min Range: -14.5224
Max Act: 13.5849. Min Act: -0.1700
Data Index: 504618 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 14.5224. Min Range: -14.5224
Max Act: 13.6474. Min Act: -0.1700
Data Index: 504611 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #19