Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4097 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.5566. Min Range: -12.5566
Max Act: 12.5566. Min Act: -0.1700
Data Index: 4605630 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.5566. Min Range: -12.5566
Max Act: 12.0566. Min Act: -0.1700
Data Index: 8459286 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.5566. Min Range: -12.5566
Max Act: 11.9941. Min Act: -0.1700
Data Index: 353229 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.5566. Min Range: -12.5566
Max Act: 11.9941. Min Act: -0.1700
Data Index: 5810751 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.5566. Min Range: -12.5566
Max Act: 11.9941. Min Act: -0.1700
Data Index: 3140497 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.5566. Min Range: -12.5566
Max Act: 11.9941. Min Act: -0.1700
Data Index: 6208604 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.5566. Min Range: -12.5566
Max Act: 11.9941. Min Act: -0.1700
Data Index: 7659914 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.5566. Min Range: -12.5566
Max Act: 11.7441. Min Act: -0.1700
Data Index: 2110248 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.5566. Min Range: -12.5566
Max Act: 11.6816. Min Act: -0.1700
Data Index: 7913965 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.5566. Min Range: -12.5566
Max Act: 11.6191. Min Act: -0.1700
Data Index: 613171 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.5566. Min Range: -12.5566
Max Act: 11.6191. Min Act: -0.1700
Data Index: 1350612 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.5566. Min Range: -12.5566
Max Act: 11.5566. Min Act: -0.1700
Data Index: 4554218 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.5566. Min Range: -12.5566
Max Act: 11.5566. Min Act: -0.1700
Data Index: 300758 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.5566. Min Range: -12.5566
Max Act: 11.4316. Min Act: -0.1700
Data Index: 5405429 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.5566. Min Range: -12.5566
Max Act: 11.4316. Min Act: -0.1700
Data Index: 1716556 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.5566. Min Range: -12.5566
Max Act: 11.4316. Min Act: -0.1700
Data Index: 1661717 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.5566. Min Range: -12.5566
Max Act: 11.4316. Min Act: -0.1700
Data Index: 1660808 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.5566. Min Range: -12.5566
Max Act: 11.3691. Min Act: -0.1700
Data Index: 2943143 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.5566. Min Range: -12.5566
Max Act: 11.3691. Min Act: -0.1700
Data Index: 2791838 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.5566. Min Range: -12.5566
Max Act: 11.3691. Min Act: -0.1700
Data Index: 1450290 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #19