Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2864 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6610. Min Range: -7.6610
Max Act: 7.6610. Min Act: -0.1700
Data Index: 2537526 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6610. Min Range: -7.6610
Max Act: 7.3485. Min Act: -0.1700
Data Index: 2954106 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6610. Min Range: -7.6610
Max Act: 7.2235. Min Act: -0.1700
Data Index: 4260219 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6610. Min Range: -7.6610
Max Act: 7.1922. Min Act: -0.1700
Data Index: 4172545 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6610. Min Range: -7.6610
Max Act: 7.1922. Min Act: -0.1700
Data Index: 4260213 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6610. Min Range: -7.6610
Max Act: 7.1610. Min Act: -0.1700
Data Index: 4040076 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6610. Min Range: -7.6610
Max Act: 7.0985. Min Act: -0.1700
Data Index: 6549952 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6610. Min Range: -7.6610
Max Act: 7.0985. Min Act: -0.1700
Data Index: 3547269 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6610. Min Range: -7.6610
Max Act: 7.0985. Min Act: -0.1700
Data Index: 5432942 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6610. Min Range: -7.6610
Max Act: 7.0985. Min Act: -0.1700
Data Index: 4194163 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6610. Min Range: -7.6610
Max Act: 7.0047. Min Act: -0.1700
Data Index: 1656570 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6610. Min Range: -7.6610
Max Act: 7.0047. Min Act: -0.1700
Data Index: 2806110 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6610. Min Range: -7.6610
Max Act: 6.9422. Min Act: -0.1700
Data Index: 5432941 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6610. Min Range: -7.6610
Max Act: 6.8485. Min Act: -0.1700
Data Index: 5856000 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6610. Min Range: -7.6610
Max Act: 6.9110. Min Act: -0.1700
Data Index: 8733737 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6610. Min Range: -7.6610
Max Act: 6.8485. Min Act: -0.1700
Data Index: 5291349 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6610. Min Range: -7.6610
Max Act: 6.8172. Min Act: -0.1700
Data Index: 2707853 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6610. Min Range: -7.6610
Max Act: 6.8485. Min Act: -0.1700
Data Index: 195828 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6610. Min Range: -7.6610
Max Act: 6.8485. Min Act: -0.1700
Data Index: 1465833 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6610. Min Range: -7.6610
Max Act: 6.8172. Min Act: -0.1700
Data Index: 1286664 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #19