Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2745 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3848. Min Range: -8.3848
Max Act: 8.3848. Min Act: -0.1700
Data Index: 5892265 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3848. Min Range: -8.3848
Max Act: 8.3848. Min Act: -0.1700
Data Index: 5333815 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3848. Min Range: -8.3848
Max Act: 8.3223. Min Act: -0.1700
Data Index: 8471079 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3848. Min Range: -8.3848
Max Act: 8.2598. Min Act: -0.1700
Data Index: 7326066 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3848. Min Range: -8.3848
Max Act: 8.2598. Min Act: -0.1700
Data Index: 5660681 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3848. Min Range: -8.3848
Max Act: 8.1348. Min Act: -0.1700
Data Index: 6023513 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3848. Min Range: -8.3848
Max Act: 8.1036. Min Act: -0.1700
Data Index: 6848954 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3848. Min Range: -8.3848
Max Act: 7.9786. Min Act: -0.1700
Data Index: 1792433 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3848. Min Range: -8.3848
Max Act: 7.7598. Min Act: -0.1700
Data Index: 2280657 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3848. Min Range: -8.3848
Max Act: 7.6661. Min Act: -0.1700
Data Index: 5589303 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3848. Min Range: -8.3848
Max Act: 7.6348. Min Act: -0.1700
Data Index: 286001 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3848. Min Range: -8.3848
Max Act: 7.6036. Min Act: -0.1700
Data Index: 3043140 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3848. Min Range: -8.3848
Max Act: 7.5723. Min Act: -0.1700
Data Index: 2322800 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3848. Min Range: -8.3848
Max Act: 7.5723. Min Act: -0.1700
Data Index: 7893419 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3848. Min Range: -8.3848
Max Act: 7.5098. Min Act: -0.1700
Data Index: 1127580 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3848. Min Range: -8.3848
Max Act: 7.5098. Min Act: -0.1700
Data Index: 5808573 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3848. Min Range: -8.3848
Max Act: 7.5098. Min Act: -0.1700
Data Index: 4563022 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3848. Min Range: -8.3848
Max Act: 7.4786. Min Act: -0.1700
Data Index: 4883402 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3848. Min Range: -8.3848
Max Act: 7.4786. Min Act: -0.1700
Data Index: 8082344 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3848. Min Range: -8.3848
Max Act: 7.5098. Min Act: -0.1700
Data Index: 3225688 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #19