Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2631 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.6466. Min Range: -7.6466
Max Act: 7.6466. Min Act: -0.1700
Data Index: 3300499 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6466. Min Range: -7.6466
Max Act: 7.6153. Min Act: -0.1700
Data Index: 7935580 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6466. Min Range: -7.6466
Max Act: 7.5528. Min Act: -0.1700
Data Index: 7502818 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6466. Min Range: -7.6466
Max Act: 7.4591. Min Act: -0.1700
Data Index: 7351197 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6466. Min Range: -7.6466
Max Act: 7.4278. Min Act: -0.1700
Data Index: 7217810 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6466. Min Range: -7.6466
Max Act: 7.3341. Min Act: -0.1700
Data Index: 623893 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6466. Min Range: -7.6466
Max Act: 7.3653. Min Act: -0.1700
Data Index: 4439990 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6466. Min Range: -7.6466
Max Act: 7.3341. Min Act: -0.1700
Data Index: 3958304 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6466. Min Range: -7.6466
Max Act: 7.3028. Min Act: -0.1700
Data Index: 3837585 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6466. Min Range: -7.6466
Max Act: 7.2716. Min Act: -0.1700
Data Index: 2437399 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6466. Min Range: -7.6466
Max Act: 7.2403. Min Act: -0.1700
Data Index: 3206197 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6466. Min Range: -7.6466
Max Act: 7.2716. Min Act: -0.1700
Data Index: 1310335 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6466. Min Range: -7.6466
Max Act: 7.2403. Min Act: -0.1700
Data Index: 4890117 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6466. Min Range: -7.6466
Max Act: 7.2403. Min Act: -0.1700
Data Index: 7372701 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6466. Min Range: -7.6466
Max Act: 7.2403. Min Act: -0.1700
Data Index: 5583076 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6466. Min Range: -7.6466
Max Act: 7.2091. Min Act: -0.1700
Data Index: 7056065 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6466. Min Range: -7.6466
Max Act: 7.1466. Min Act: -0.1700
Data Index: 8580742 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6466. Min Range: -7.6466
Max Act: 7.1778. Min Act: -0.1700
Data Index: 3060436 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6466. Min Range: -7.6466
Max Act: 7.1466. Min Act: -0.1700
Data Index: 6705262 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6466. Min Range: -7.6466
Max Act: 7.1778. Min Act: -0.1700
Data Index: 3668666 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #19