Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4334 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8179. Min Range: -3.8179
Max Act: 3.8179. Min Act: -0.1700
Data Index: 1684070 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8179. Min Range: -3.8179
Max Act: 3.7553. Min Act: -0.1700
Data Index: 4321559 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8179. Min Range: -3.8179
Max Act: 3.6927. Min Act: -0.1700
Data Index: 3113309 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8179. Min Range: -3.8179
Max Act: 3.6614. Min Act: -0.1700
Data Index: 2289562 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8179. Min Range: -3.8179
Max Act: 3.6614. Min Act: -0.1700
Data Index: 3711365 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8179. Min Range: -3.8179
Max Act: 3.6302. Min Act: -0.1700
Data Index: 5929276 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8179. Min Range: -3.8179
Max Act: 3.5989. Min Act: -0.1700
Data Index: 543791 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8179. Min Range: -3.8179
Max Act: 3.5989. Min Act: -0.1700
Data Index: 3383158 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8179. Min Range: -3.8179
Max Act: 3.5362. Min Act: -0.1700
Data Index: 5194440 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8179. Min Range: -3.8179
Max Act: 3.5362. Min Act: -0.1700
Data Index: 1618857 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8179. Min Range: -3.8179
Max Act: 3.4893. Min Act: -0.1700
Data Index: 6364696 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8179. Min Range: -3.8179
Max Act: 3.4893. Min Act: -0.1700
Data Index: 786967 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8179. Min Range: -3.8179
Max Act: 3.4893. Min Act: -0.1700
Data Index: 4842920 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8179. Min Range: -3.8179
Max Act: 3.4893. Min Act: -0.1700
Data Index: 819094 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8179. Min Range: -3.8179
Max Act: 3.4423. Min Act: -0.1700
Data Index: 274656 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8179. Min Range: -3.8179
Max Act: 3.4266. Min Act: -0.1700
Data Index: 8095368 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8179. Min Range: -3.8179
Max Act: 3.4266. Min Act: -0.1700
Data Index: 2289561 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8179. Min Range: -3.8179
Max Act: 3.4266. Min Act: -0.1700
Data Index: 5514619 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8179. Min Range: -3.8179
Max Act: 3.4266. Min Act: -0.1700
Data Index: 801950 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8179. Min Range: -3.8179
Max Act: 3.4109. Min Act: -0.1700
Data Index: 2332497 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #19