Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3212 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5379. Min Range: -7.5379
Max Act: 7.5379. Min Act: -0.1700
Data Index: 2524188 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5379. Min Range: -7.5379
Max Act: 7.5066. Min Act: -0.1700
Data Index: 6927104 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5379. Min Range: -7.5379
Max Act: 7.4754. Min Act: -0.1700
Data Index: 8596914 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5379. Min Range: -7.5379
Max Act: 7.4754. Min Act: -0.1700
Data Index: 1675223 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5379. Min Range: -7.5379
Max Act: 7.3191. Min Act: -0.1700
Data Index: 7729371 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5379. Min Range: -7.5379
Max Act: 7.1941. Min Act: -0.1700
Data Index: 5050426 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5379. Min Range: -7.5379
Max Act: 7.1629. Min Act: -0.1700
Data Index: 8371059 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5379. Min Range: -7.5379
Max Act: 7.1629. Min Act: -0.1700
Data Index: 1566257 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5379. Min Range: -7.5379
Max Act: 7.1316. Min Act: -0.1700
Data Index: 3118076 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5379. Min Range: -7.5379
Max Act: 7.1316. Min Act: -0.1700
Data Index: 3702592 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5379. Min Range: -7.5379
Max Act: 7.0379. Min Act: -0.1700
Data Index: 3384100 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5379. Min Range: -7.5379
Max Act: 7.0691. Min Act: -0.1700
Data Index: 3059830 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5379. Min Range: -7.5379
Max Act: 7.0379. Min Act: -0.1700
Data Index: 4215974 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5379. Min Range: -7.5379
Max Act: 7.0691. Min Act: -0.1700
Data Index: 8805165 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5379. Min Range: -7.5379
Max Act: 7.0379. Min Act: -0.1700
Data Index: 5407685 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5379. Min Range: -7.5379
Max Act: 7.0379. Min Act: -0.1700
Data Index: 4906420 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5379. Min Range: -7.5379
Max Act: 7.0379. Min Act: -0.1700
Data Index: 381591 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5379. Min Range: -7.5379
Max Act: 7.0379. Min Act: -0.1700
Data Index: 3923568 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5379. Min Range: -7.5379
Max Act: 6.9754. Min Act: -0.1700
Data Index: 2133159 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5379. Min Range: -7.5379
Max Act: 7.0066. Min Act: -0.1700
Data Index: 5237742 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #19