Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3144 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5675. Min Range: -4.5675
Max Act: 4.5675. Min Act: -0.1700
Data Index: 6070463 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5675. Min Range: -4.5675
Max Act: 4.5363. Min Act: -0.1700
Data Index: 7783200 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5675. Min Range: -4.5675
Max Act: 4.5363. Min Act: -0.1700
Data Index: 5540300 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5675. Min Range: -4.5675
Max Act: 4.5363. Min Act: -0.1700
Data Index: 8791434 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5675. Min Range: -4.5675
Max Act: 4.5050. Min Act: -0.1700
Data Index: 2903699 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5675. Min Range: -4.5675
Max Act: 4.4425. Min Act: -0.1700
Data Index: 4925626 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5675. Min Range: -4.5675
Max Act: 4.4113. Min Act: -0.1700
Data Index: 8143785 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5675. Min Range: -4.5675
Max Act: 4.4425. Min Act: -0.1700
Data Index: 4023336 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5675. Min Range: -4.5675
Max Act: 4.4425. Min Act: -0.1700
Data Index: 6379758 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5675. Min Range: -4.5675
Max Act: 4.4113. Min Act: -0.1700
Data Index: 692727 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5675. Min Range: -4.5675
Max Act: 4.3800. Min Act: -0.1700
Data Index: 7355535 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5675. Min Range: -4.5675
Max Act: 4.3800. Min Act: -0.1700
Data Index: 7991558 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5675. Min Range: -4.5675
Max Act: 4.3800. Min Act: -0.1700
Data Index: 4335313 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5675. Min Range: -4.5675
Max Act: 4.3800. Min Act: -0.1700
Data Index: 4161380 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5675. Min Range: -4.5675
Max Act: 4.3488. Min Act: -0.1700
Data Index: 2961578 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5675. Min Range: -4.5675
Max Act: 4.3488. Min Act: -0.1700
Data Index: 3278262 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5675. Min Range: -4.5675
Max Act: 4.3175. Min Act: -0.1700
Data Index: 2538799 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5675. Min Range: -4.5675
Max Act: 4.2863. Min Act: -0.1700
Data Index: 6728782 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5675. Min Range: -4.5675
Max Act: 4.3175. Min Act: -0.1700
Data Index: 4363422 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5675. Min Range: -4.5675
Max Act: 4.3488. Min Act: -0.1700
Data Index: 4150304 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19