Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 896 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1341. Min Range: -4.1341
Max Act: 4.1341. Min Act: -0.1700
Data Index: 1239512 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1341. Min Range: -4.1341
Max Act: 4.0716. Min Act: -0.1700
Data Index: 4886992 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1341. Min Range: -4.1341
Max Act: 4.0404. Min Act: -0.1700
Data Index: 3928629 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1341. Min Range: -4.1341
Max Act: 3.9779. Min Act: -0.1700
Data Index: 5666121 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1341. Min Range: -4.1341
Max Act: 3.9153. Min Act: -0.1700
Data Index: 7649972 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1341. Min Range: -4.1341
Max Act: 3.9466. Min Act: -0.1700
Data Index: 651389 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1341. Min Range: -4.1341
Max Act: 3.9153. Min Act: -0.1700
Data Index: 7105049 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1341. Min Range: -4.1341
Max Act: 3.9153. Min Act: -0.1700
Data Index: 1867453 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1341. Min Range: -4.1341
Max Act: 3.9153. Min Act: -0.1700
Data Index: 8236194 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1341. Min Range: -4.1341
Max Act: 3.8841. Min Act: -0.1700
Data Index: 4914590 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1341. Min Range: -4.1341
Max Act: 3.8841. Min Act: -0.1700
Data Index: 8577419 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1341. Min Range: -4.1341
Max Act: 3.8841. Min Act: -0.1700
Data Index: 8415119 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1341. Min Range: -4.1341
Max Act: 3.8841. Min Act: -0.1700
Data Index: 17817 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1341. Min Range: -4.1341
Max Act: 3.8528. Min Act: -0.1700
Data Index: 934795 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1341. Min Range: -4.1341
Max Act: 3.8528. Min Act: -0.1700
Data Index: 1241016 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1341. Min Range: -4.1341
Max Act: 3.8528. Min Act: -0.1700
Data Index: 7935789 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1341. Min Range: -4.1341
Max Act: 3.8528. Min Act: -0.1700
Data Index: 3423129 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1341. Min Range: -4.1341
Max Act: 3.8528. Min Act: -0.1700
Data Index: 526682 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1341. Min Range: -4.1341
Max Act: 3.8528. Min Act: -0.1700
Data Index: 1739662 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1341. Min Range: -4.1341
Max Act: 3.7902. Min Act: -0.1700
Data Index: 5935580 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #19