Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1862 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0018. Min Range: -5.0018
Max Act: 5.0018. Min Act: -0.1700
Data Index: 6583750 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0018. Min Range: -5.0018
Max Act: 4.7205. Min Act: -0.1700
Data Index: 2680284 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0018. Min Range: -5.0018
Max Act: 4.7205. Min Act: -0.1700
Data Index: 3567347 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0018. Min Range: -5.0018
Max Act: 4.6893. Min Act: -0.1700
Data Index: 7454752 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0018. Min Range: -5.0018
Max Act: 4.6580. Min Act: -0.1700
Data Index: 7413248 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0018. Min Range: -5.0018
Max Act: 4.7205. Min Act: -0.1700
Data Index: 3423157 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0018. Min Range: -5.0018
Max Act: 4.6268. Min Act: -0.1700
Data Index: 2789017 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0018. Min Range: -5.0018
Max Act: 4.6268. Min Act: -0.1700
Data Index: 5397971 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0018. Min Range: -5.0018
Max Act: 4.5955. Min Act: -0.1700
Data Index: 3127998 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0018. Min Range: -5.0018
Max Act: 4.5955. Min Act: -0.1700
Data Index: 7892487 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0018. Min Range: -5.0018
Max Act: 4.5955. Min Act: -0.1700
Data Index: 4754645 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0018. Min Range: -5.0018
Max Act: 4.5955. Min Act: -0.1700
Data Index: 3203430 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0018. Min Range: -5.0018
Max Act: 4.5955. Min Act: -0.1700
Data Index: 829941 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0018. Min Range: -5.0018
Max Act: 4.5955. Min Act: -0.1700
Data Index: 3458016 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0018. Min Range: -5.0018
Max Act: 4.5955. Min Act: -0.1700
Data Index: 6959006 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0018. Min Range: -5.0018
Max Act: 4.5643. Min Act: -0.1700
Data Index: 8302379 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0018. Min Range: -5.0018
Max Act: 4.5643. Min Act: -0.1700
Data Index: 8367140 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0018. Min Range: -5.0018
Max Act: 4.5330. Min Act: -0.1700
Data Index: 7608529 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0018. Min Range: -5.0018
Max Act: 4.5330. Min Act: -0.1700
Data Index: 7804046 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0018. Min Range: -5.0018
Max Act: 4.5643. Min Act: -0.1700
Data Index: 5697044 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #19