Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2615 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9283. Min Range: -5.9283
Max Act: 5.9283. Min Act: -0.1700
Data Index: 4610434 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9283. Min Range: -5.9283
Max Act: 5.5533. Min Act: -0.1700
Data Index: 7594466 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9283. Min Range: -5.9283
Max Act: 5.4283. Min Act: -0.1700
Data Index: 3247114 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9283. Min Range: -5.9283
Max Act: 5.3971. Min Act: -0.1700
Data Index: 5868794 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9283. Min Range: -5.9283
Max Act: 5.2721. Min Act: -0.1700
Data Index: 2838543 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9283. Min Range: -5.9283
Max Act: 5.2721. Min Act: -0.1700
Data Index: 7821961 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9283. Min Range: -5.9283
Max Act: 5.2408. Min Act: -0.1700
Data Index: 4794934 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9283. Min Range: -5.9283
Max Act: 5.2096. Min Act: -0.1700
Data Index: 1615510 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9283. Min Range: -5.9283
Max Act: 5.1471. Min Act: -0.1700
Data Index: 1044603 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9283. Min Range: -5.9283
Max Act: 5.1471. Min Act: -0.1700
Data Index: 8365360 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9283. Min Range: -5.9283
Max Act: 5.1158. Min Act: -0.1700
Data Index: 4181809 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9283. Min Range: -5.9283
Max Act: 5.1158. Min Act: -0.1700
Data Index: 5320574 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9283. Min Range: -5.9283
Max Act: 5.0846. Min Act: -0.1700
Data Index: 1783790 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9283. Min Range: -5.9283
Max Act: 5.0846. Min Act: -0.1700
Data Index: 7994835 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9283. Min Range: -5.9283
Max Act: 5.0533. Min Act: -0.1700
Data Index: 2596628 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9283. Min Range: -5.9283
Max Act: 5.0221. Min Act: -0.1700
Data Index: 1845026 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9283. Min Range: -5.9283
Max Act: 5.0221. Min Act: -0.1700
Data Index: 3022451 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9283. Min Range: -5.9283
Max Act: 4.9908. Min Act: -0.1700
Data Index: 8348069 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9283. Min Range: -5.9283
Max Act: 4.9908. Min Act: -0.1700
Data Index: 663385 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9283. Min Range: -5.9283
Max Act: 4.9908. Min Act: -0.1700
Data Index: 1779020 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #19