Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4382 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4273. Min Range: -6.4273
Max Act: 6.4273. Min Act: -0.1700
Data Index: 2959411 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4273. Min Range: -6.4273
Max Act: 6.2398. Min Act: -0.1700
Data Index: 3997236 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4273. Min Range: -6.4273
Max Act: 6.2398. Min Act: -0.1700
Data Index: 8337086 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4273. Min Range: -6.4273
Max Act: 6.1773. Min Act: -0.1700
Data Index: 396992 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4273. Min Range: -6.4273
Max Act: 6.1773. Min Act: -0.1700
Data Index: 1632740 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4273. Min Range: -6.4273
Max Act: 6.1148. Min Act: -0.1700
Data Index: 8651164 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4273. Min Range: -6.4273
Max Act: 6.1460. Min Act: -0.1700
Data Index: 6734055 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4273. Min Range: -6.4273
Max Act: 6.1148. Min Act: -0.1700
Data Index: 4957180 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4273. Min Range: -6.4273
Max Act: 6.1148. Min Act: -0.1700
Data Index: 1632739 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4273. Min Range: -6.4273
Max Act: 6.0835. Min Act: -0.1700
Data Index: 4957171 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4273. Min Range: -6.4273
Max Act: 6.0523. Min Act: -0.1700
Data Index: 6315745 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4273. Min Range: -6.4273
Max Act: 6.0210. Min Act: -0.1700
Data Index: 4957167 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4273. Min Range: -6.4273
Max Act: 6.0210. Min Act: -0.1700
Data Index: 4957173 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4273. Min Range: -6.4273
Max Act: 6.0210. Min Act: -0.1700
Data Index: 8367990 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4273. Min Range: -6.4273
Max Act: 5.9898. Min Act: -0.1700
Data Index: 8367995 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4273. Min Range: -6.4273
Max Act: 5.9585. Min Act: -0.1700
Data Index: 4029465 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4273. Min Range: -6.4273
Max Act: 5.9273. Min Act: -0.1700
Data Index: 6959127 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4273. Min Range: -6.4273
Max Act: 5.9273. Min Act: -0.1700
Data Index: 3681966 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4273. Min Range: -6.4273
Max Act: 5.8960. Min Act: -0.1700
Data Index: 7268775 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4273. Min Range: -6.4273
Max Act: 5.8960. Min Act: -0.1700
Data Index: 6315747 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19