Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4339 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0364. Min Range: -6.0364
Max Act: 6.0364. Min Act: -0.1700
Data Index: 6482133 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0364. Min Range: -6.0364
Max Act: 6.0052. Min Act: -0.1700
Data Index: 2575915 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0364. Min Range: -6.0364
Max Act: 5.9739. Min Act: -0.1700
Data Index: 2849048 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0364. Min Range: -6.0364
Max Act: 5.9427. Min Act: -0.1700
Data Index: 1878045 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0364. Min Range: -6.0364
Max Act: 5.9427. Min Act: -0.1700
Data Index: 4348581 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0364. Min Range: -6.0364
Max Act: 5.8802. Min Act: -0.1700
Data Index: 479999 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0364. Min Range: -6.0364
Max Act: 5.8802. Min Act: -0.1700
Data Index: 3575625 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0364. Min Range: -6.0364
Max Act: 5.8802. Min Act: -0.1700
Data Index: 7948788 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0364. Min Range: -6.0364
Max Act: 5.8489. Min Act: -0.1700
Data Index: 4298170 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0364. Min Range: -6.0364
Max Act: 5.8489. Min Act: -0.1700
Data Index: 8151037 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0364. Min Range: -6.0364
Max Act: 5.8177. Min Act: -0.1700
Data Index: 5749928 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0364. Min Range: -6.0364
Max Act: 5.8177. Min Act: -0.1700
Data Index: 8258759 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0364. Min Range: -6.0364
Max Act: 5.8177. Min Act: -0.1700
Data Index: 6507833 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0364. Min Range: -6.0364
Max Act: 5.8177. Min Act: -0.1700
Data Index: 3985432 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0364. Min Range: -6.0364
Max Act: 5.8177. Min Act: -0.1700
Data Index: 6917081 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0364. Min Range: -6.0364
Max Act: 5.7864. Min Act: -0.1700
Data Index: 3821740 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0364. Min Range: -6.0364
Max Act: 5.8177. Min Act: -0.1700
Data Index: 4717667 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0364. Min Range: -6.0364
Max Act: 5.7864. Min Act: -0.1700
Data Index: 935142 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0364. Min Range: -6.0364
Max Act: 5.7864. Min Act: -0.1700
Data Index: 2986554 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0364. Min Range: -6.0364
Max Act: 5.7552. Min Act: -0.1700
Data Index: 5088006 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #19