Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1935 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5175. Min Range: -4.5175
Max Act: 4.5175. Min Act: -0.1700
Data Index: 6841912 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5175. Min Range: -4.5175
Max Act: 4.4863. Min Act: -0.1700
Data Index: 4627533 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5175. Min Range: -4.5175
Max Act: 4.3925. Min Act: -0.1700
Data Index: 898310 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5175. Min Range: -4.5175
Max Act: 4.3613. Min Act: -0.1700
Data Index: 6082595 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5175. Min Range: -4.5175
Max Act: 4.3925. Min Act: -0.1700
Data Index: 1719001 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5175. Min Range: -4.5175
Max Act: 4.3300. Min Act: -0.1700
Data Index: 6947892 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5175. Min Range: -4.5175
Max Act: 4.2363. Min Act: -0.1700
Data Index: 7377553 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5175. Min Range: -4.5175
Max Act: 4.2675. Min Act: -0.1700
Data Index: 4845917 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5175. Min Range: -4.5175
Max Act: 4.2675. Min Act: -0.1700
Data Index: 4159573 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5175. Min Range: -4.5175
Max Act: 4.2675. Min Act: -0.1700
Data Index: 7718483 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5175. Min Range: -4.5175
Max Act: 4.2675. Min Act: -0.1700
Data Index: 5896197 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5175. Min Range: -4.5175
Max Act: 4.2675. Min Act: -0.1700
Data Index: 8703952 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5175. Min Range: -4.5175
Max Act: 4.2675. Min Act: -0.1700
Data Index: 8166905 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5175. Min Range: -4.5175
Max Act: 4.2675. Min Act: -0.1700
Data Index: 1761548 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5175. Min Range: -4.5175
Max Act: 4.2675. Min Act: -0.1700
Data Index: 2900131 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5175. Min Range: -4.5175
Max Act: 4.2363. Min Act: -0.1700
Data Index: 8100533 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5175. Min Range: -4.5175
Max Act: 4.2050. Min Act: -0.1700
Data Index: 310120 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5175. Min Range: -4.5175
Max Act: 4.2050. Min Act: -0.1700
Data Index: 8530343 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5175. Min Range: -4.5175
Max Act: 4.2363. Min Act: -0.1700
Data Index: 5368036 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5175. Min Range: -4.5175
Max Act: 4.1738. Min Act: -0.1700
Data Index: 5163748 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #19