Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3345 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4754. Min Range: -7.4754
Max Act: 7.4754. Min Act: -0.1700
Data Index: 3646817 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4754. Min Range: -7.4754
Max Act: 7.2879. Min Act: -0.1700
Data Index: 2696325 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4754. Min Range: -7.4754
Max Act: 7.2254. Min Act: -0.1700
Data Index: 2926394 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4754. Min Range: -7.4754
Max Act: 7.2254. Min Act: -0.1700
Data Index: 7615497 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4754. Min Range: -7.4754
Max Act: 7.1629. Min Act: -0.1700
Data Index: 2051508 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4754. Min Range: -7.4754
Max Act: 7.1316. Min Act: -0.1700
Data Index: 565669 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4754. Min Range: -7.4754
Max Act: 7.1004. Min Act: -0.1700
Data Index: 1988733 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4754. Min Range: -7.4754
Max Act: 7.1004. Min Act: -0.1700
Data Index: 6648937 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4754. Min Range: -7.4754
Max Act: 7.0691. Min Act: -0.1700
Data Index: 267312 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4754. Min Range: -7.4754
Max Act: 7.0691. Min Act: -0.1700
Data Index: 5576967 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4754. Min Range: -7.4754
Max Act: 7.0691. Min Act: -0.1700
Data Index: 2385446 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4754. Min Range: -7.4754
Max Act: 7.0691. Min Act: -0.1700
Data Index: 5169589 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4754. Min Range: -7.4754
Max Act: 7.0379. Min Act: -0.1700
Data Index: 8125057 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4754. Min Range: -7.4754
Max Act: 7.0379. Min Act: -0.1700
Data Index: 4118485 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4754. Min Range: -7.4754
Max Act: 7.0066. Min Act: -0.1700
Data Index: 3990121 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4754. Min Range: -7.4754
Max Act: 6.9441. Min Act: -0.1700
Data Index: 6318374 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4754. Min Range: -7.4754
Max Act: 6.9754. Min Act: -0.1700
Data Index: 8298242 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4754. Min Range: -7.4754
Max Act: 6.9441. Min Act: -0.1700
Data Index: 5044493 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4754. Min Range: -7.4754
Max Act: 6.9441. Min Act: -0.1700
Data Index: 4835084 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4754. Min Range: -7.4754
Max Act: 6.9441. Min Act: -0.1700
Data Index: 5085634 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #19