Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1547 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4085. Min Range: -4.4085
Max Act: 4.4085. Min Act: -0.1700
Data Index: 3863018 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4085. Min Range: -4.4085
Max Act: 4.2522. Min Act: -0.1700
Data Index: 3751781 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4085. Min Range: -4.4085
Max Act: 4.2522. Min Act: -0.1700
Data Index: 1956872 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4085. Min Range: -4.4085
Max Act: 4.2210. Min Act: -0.1700
Data Index: 6257599 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4085. Min Range: -4.4085
Max Act: 4.2522. Min Act: -0.1700
Data Index: 8549641 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4085. Min Range: -4.4085
Max Act: 4.1585. Min Act: -0.1700
Data Index: 3827253 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4085. Min Range: -4.4085
Max Act: 4.1272. Min Act: -0.1700
Data Index: 7337806 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4085. Min Range: -4.4085
Max Act: 4.1272. Min Act: -0.1700
Data Index: 5957575 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4085. Min Range: -4.4085
Max Act: 4.0959. Min Act: -0.1700
Data Index: 6828076 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4085. Min Range: -4.4085
Max Act: 4.0959. Min Act: -0.1700
Data Index: 473684 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4085. Min Range: -4.4085
Max Act: 4.1272. Min Act: -0.1700
Data Index: 5874457 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4085. Min Range: -4.4085
Max Act: 4.0959. Min Act: -0.1700
Data Index: 8622664 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4085. Min Range: -4.4085
Max Act: 4.0959. Min Act: -0.1700
Data Index: 2915678 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4085. Min Range: -4.4085
Max Act: 4.0959. Min Act: -0.1700
Data Index: 4081688 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4085. Min Range: -4.4085
Max Act: 4.0647. Min Act: -0.1700
Data Index: 2189749 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4085. Min Range: -4.4085
Max Act: 4.0334. Min Act: -0.1700
Data Index: 6794048 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4085. Min Range: -4.4085
Max Act: 4.0334. Min Act: -0.1700
Data Index: 5723507 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4085. Min Range: -4.4085
Max Act: 4.0334. Min Act: -0.1700
Data Index: 2906072 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4085. Min Range: -4.4085
Max Act: 4.0334. Min Act: -0.1700
Data Index: 4315031 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4085. Min Range: -4.4085
Max Act: 4.0334. Min Act: -0.1700
Data Index: 353366 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #19