Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3902 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7557. Min Range: -5.7557
Max Act: 5.7557. Min Act: -0.1700
Data Index: 6058648 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7557. Min Range: -5.7557
Max Act: 5.6932. Min Act: -0.1700
Data Index: 8747081 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7557. Min Range: -5.7557
Max Act: 5.6620. Min Act: -0.1700
Data Index: 3218219 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7557. Min Range: -5.7557
Max Act: 5.6620. Min Act: -0.1700
Data Index: 5919732 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7557. Min Range: -5.7557
Max Act: 5.6307. Min Act: -0.1700
Data Index: 5505472 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7557. Min Range: -5.7557
Max Act: 5.5682. Min Act: -0.1700
Data Index: 6743650 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7557. Min Range: -5.7557
Max Act: 5.5682. Min Act: -0.1700
Data Index: 5919729 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7557. Min Range: -5.7557
Max Act: 5.5682. Min Act: -0.1700
Data Index: 4094770 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7557. Min Range: -5.7557
Max Act: 5.5682. Min Act: -0.1700
Data Index: 6094385 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7557. Min Range: -5.7557
Max Act: 5.5682. Min Act: -0.1700
Data Index: 6905469 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7557. Min Range: -5.7557
Max Act: 5.5370. Min Act: -0.1700
Data Index: 2266517 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7557. Min Range: -5.7557
Max Act: 5.5370. Min Act: -0.1700
Data Index: 5078916 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7557. Min Range: -5.7557
Max Act: 5.5682. Min Act: -0.1700
Data Index: 4743467 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7557. Min Range: -5.7557
Max Act: 5.5370. Min Act: -0.1700
Data Index: 7791765 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7557. Min Range: -5.7557
Max Act: 5.5057. Min Act: -0.1700
Data Index: 5096293 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7557. Min Range: -5.7557
Max Act: 5.5057. Min Act: -0.1700
Data Index: 6058650 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7557. Min Range: -5.7557
Max Act: 5.5057. Min Act: -0.1700
Data Index: 392653 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7557. Min Range: -5.7557
Max Act: 5.4745. Min Act: -0.1700
Data Index: 6920690 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7557. Min Range: -5.7557
Max Act: 5.5057. Min Act: -0.1700
Data Index: 1141501 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7557. Min Range: -5.7557
Max Act: 5.5057. Min Act: -0.1700
Data Index: 5939459 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #19