Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 936 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7318. Min Range: -5.7318
Max Act: 5.7318. Min Act: -0.1700
Data Index: 2940258 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7318. Min Range: -5.7318
Max Act: 5.6693. Min Act: -0.1700
Data Index: 1807112 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7318. Min Range: -5.7318
Max Act: 5.5443. Min Act: -0.1700
Data Index: 6484082 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7318. Min Range: -5.7318
Max Act: 5.3880. Min Act: -0.1700
Data Index: 6671548 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7318. Min Range: -5.7318
Max Act: 5.4193. Min Act: -0.1700
Data Index: 5748025 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7318. Min Range: -5.7318
Max Act: 5.3255. Min Act: -0.1700
Data Index: 5748024 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7318. Min Range: -5.7318
Max Act: 5.3255. Min Act: -0.1700
Data Index: 3796642 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7318. Min Range: -5.7318
Max Act: 5.3255. Min Act: -0.1700
Data Index: 8475980 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7318. Min Range: -5.7318
Max Act: 5.2943. Min Act: -0.1700
Data Index: 8279683 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7318. Min Range: -5.7318
Max Act: 5.2943. Min Act: -0.1700
Data Index: 8277096 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7318. Min Range: -5.7318
Max Act: 5.2630. Min Act: -0.1700
Data Index: 5278203 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7318. Min Range: -5.7318
Max Act: 5.2318. Min Act: -0.1700
Data Index: 4386635 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7318. Min Range: -5.7318
Max Act: 5.2318. Min Act: -0.1700
Data Index: 4512727 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7318. Min Range: -5.7318
Max Act: 5.2318. Min Act: -0.1700
Data Index: 3572552 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7318. Min Range: -5.7318
Max Act: 5.2005. Min Act: -0.1700
Data Index: 3588924 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7318. Min Range: -5.7318
Max Act: 5.1693. Min Act: -0.1700
Data Index: 986919 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7318. Min Range: -5.7318
Max Act: 5.1693. Min Act: -0.1700
Data Index: 4665024 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7318. Min Range: -5.7318
Max Act: 5.2005. Min Act: -0.1700
Data Index: 8160884 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7318. Min Range: -5.7318
Max Act: 5.1693. Min Act: -0.1700
Data Index: 1287073 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7318. Min Range: -5.7318
Max Act: 5.1693. Min Act: -0.1700
Data Index: 3523098 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #19