Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3441 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1002. Min Range: -6.1002
Max Act: 6.1002. Min Act: -0.1700
Data Index: 8485538 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1002. Min Range: -6.1002
Max Act: 5.9439. Min Act: -0.1700
Data Index: 3266262 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1002. Min Range: -6.1002
Max Act: 5.8502. Min Act: -0.1700
Data Index: 3387607 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1002. Min Range: -6.1002
Max Act: 5.7564. Min Act: -0.1700
Data Index: 3778971 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1002. Min Range: -6.1002
Max Act: 5.7252. Min Act: -0.1700
Data Index: 5775635 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1002. Min Range: -6.1002
Max Act: 5.6939. Min Act: -0.1700
Data Index: 6501824 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1002. Min Range: -6.1002
Max Act: 5.6939. Min Act: -0.1700
Data Index: 1764364 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1002. Min Range: -6.1002
Max Act: 5.6939. Min Act: -0.1700
Data Index: 7223424 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1002. Min Range: -6.1002
Max Act: 5.6314. Min Act: -0.1700
Data Index: 5525056 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1002. Min Range: -6.1002
Max Act: 5.5689. Min Act: -0.1700
Data Index: 5492999 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1002. Min Range: -6.1002
Max Act: 5.6002. Min Act: -0.1700
Data Index: 4102281 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1002. Min Range: -6.1002
Max Act: 5.5689. Min Act: -0.1700
Data Index: 161366 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1002. Min Range: -6.1002
Max Act: 5.5689. Min Act: -0.1700
Data Index: 3085156 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1002. Min Range: -6.1002
Max Act: 5.5377. Min Act: -0.1700
Data Index: 1208393 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1002. Min Range: -6.1002
Max Act: 5.5689. Min Act: -0.1700
Data Index: 579369 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1002. Min Range: -6.1002
Max Act: 5.5689. Min Act: -0.1700
Data Index: 3830320 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1002. Min Range: -6.1002
Max Act: 5.5689. Min Act: -0.1700
Data Index: 6213282 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1002. Min Range: -6.1002
Max Act: 5.6002. Min Act: -0.1700
Data Index: 4232306 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1002. Min Range: -6.1002
Max Act: 5.5377. Min Act: -0.1700
Data Index: 6552519 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1002. Min Range: -6.1002
Max Act: 5.5377. Min Act: -0.1700
Data Index: 3611187 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #19