Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3067 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7927. Min Range: -7.7927
Max Act: 7.7927. Min Act: -0.1700
Data Index: 249255 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7927. Min Range: -7.7927
Max Act: 7.7302. Min Act: -0.1700
Data Index: 7823598 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7927. Min Range: -7.7927
Max Act: 7.6677. Min Act: -0.1700
Data Index: 6429448 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7927. Min Range: -7.7927
Max Act: 7.6052. Min Act: -0.1700
Data Index: 1474619 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7927. Min Range: -7.7927
Max Act: 7.5427. Min Act: -0.1700
Data Index: 2774834 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7927. Min Range: -7.7927
Max Act: 7.4802. Min Act: -0.1700
Data Index: 6520499 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7927. Min Range: -7.7927
Max Act: 7.4802. Min Act: -0.1700
Data Index: 344328 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7927. Min Range: -7.7927
Max Act: 7.4802. Min Act: -0.1700
Data Index: 136242 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7927. Min Range: -7.7927
Max Act: 7.4489. Min Act: -0.1700
Data Index: 7965655 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7927. Min Range: -7.7927
Max Act: 7.4489. Min Act: -0.1700
Data Index: 452364 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7927. Min Range: -7.7927
Max Act: 7.4177. Min Act: -0.1700
Data Index: 4983410 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7927. Min Range: -7.7927
Max Act: 7.3864. Min Act: -0.1700
Data Index: 1431851 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7927. Min Range: -7.7927
Max Act: 7.3864. Min Act: -0.1700
Data Index: 4615094 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7927. Min Range: -7.7927
Max Act: 7.3864. Min Act: -0.1700
Data Index: 304682 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7927. Min Range: -7.7927
Max Act: 7.3864. Min Act: -0.1700
Data Index: 2957070 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7927. Min Range: -7.7927
Max Act: 7.3552. Min Act: -0.1700
Data Index: 5456747 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7927. Min Range: -7.7927
Max Act: 7.3552. Min Act: -0.1700
Data Index: 3888228 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7927. Min Range: -7.7927
Max Act: 7.3552. Min Act: -0.1700
Data Index: 1933602 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7927. Min Range: -7.7927
Max Act: 7.3552. Min Act: -0.1700
Data Index: 2954037 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7927. Min Range: -7.7927
Max Act: 7.3239. Min Act: -0.1700
Data Index: 3215235 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #19