Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3747 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3985. Min Range: -6.3985
Max Act: 6.3985. Min Act: -0.1700
Data Index: 3323868 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3985. Min Range: -6.3985
Max Act: 6.3360. Min Act: -0.1700
Data Index: 802792 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3985. Min Range: -6.3985
Max Act: 6.3360. Min Act: -0.1700
Data Index: 4216975 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3985. Min Range: -6.3985
Max Act: 6.2735. Min Act: -0.1700
Data Index: 3911425 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3985. Min Range: -6.3985
Max Act: 6.2110. Min Act: -0.1700
Data Index: 2351544 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3985. Min Range: -6.3985
Max Act: 6.1797. Min Act: -0.1700
Data Index: 185614 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3985. Min Range: -6.3985
Max Act: 6.1485. Min Act: -0.1700
Data Index: 3376424 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3985. Min Range: -6.3985
Max Act: 6.1172. Min Act: -0.1700
Data Index: 4926077 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3985. Min Range: -6.3985
Max Act: 6.0547. Min Act: -0.1700
Data Index: 2828327 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3985. Min Range: -6.3985
Max Act: 6.0547. Min Act: -0.1700
Data Index: 195842 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3985. Min Range: -6.3985
Max Act: 5.9610. Min Act: -0.1700
Data Index: 8286362 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3985. Min Range: -6.3985
Max Act: 5.9297. Min Act: -0.1700
Data Index: 5820005 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3985. Min Range: -6.3985
Max Act: 5.9297. Min Act: -0.1700
Data Index: 6314092 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3985. Min Range: -6.3985
Max Act: 5.9297. Min Act: -0.1700
Data Index: 3456111 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3985. Min Range: -6.3985
Max Act: 5.9610. Min Act: -0.1700
Data Index: 1651710 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3985. Min Range: -6.3985
Max Act: 5.9297. Min Act: -0.1700
Data Index: 7217649 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3985. Min Range: -6.3985
Max Act: 5.8672. Min Act: -0.1700
Data Index: 8216735 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3985. Min Range: -6.3985
Max Act: 5.8985. Min Act: -0.1700
Data Index: 8198486 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3985. Min Range: -6.3985
Max Act: 5.8672. Min Act: -0.1700
Data Index: 2548137 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3985. Min Range: -6.3985
Max Act: 5.8672. Min Act: -0.1700
Data Index: 4826250 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #19