Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3910 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9098. Min Range: -7.9098
Max Act: 7.9098. Min Act: -0.1700
Data Index: 6818308 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9098. Min Range: -7.9098
Max Act: 7.7223. Min Act: -0.1700
Data Index: 7709349 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9098. Min Range: -7.9098
Max Act: 7.6598. Min Act: -0.1700
Data Index: 2926613 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9098. Min Range: -7.9098
Max Act: 7.5661. Min Act: -0.1700
Data Index: 1124027 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9098. Min Range: -7.9098
Max Act: 7.5661. Min Act: -0.1700
Data Index: 5913583 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9098. Min Range: -7.9098
Max Act: 7.5661. Min Act: -0.1700
Data Index: 6185164 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9098. Min Range: -7.9098
Max Act: 7.5661. Min Act: -0.1700
Data Index: 8232688 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9098. Min Range: -7.9098
Max Act: 7.5036. Min Act: -0.1700
Data Index: 3851204 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9098. Min Range: -7.9098
Max Act: 7.5348. Min Act: -0.1700
Data Index: 5858109 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9098. Min Range: -7.9098
Max Act: 7.4723. Min Act: -0.1700
Data Index: 6273527 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9098. Min Range: -7.9098
Max Act: 7.4723. Min Act: -0.1700
Data Index: 3009210 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9098. Min Range: -7.9098
Max Act: 7.4411. Min Act: -0.1700
Data Index: 3513455 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9098. Min Range: -7.9098
Max Act: 7.4098. Min Act: -0.1700
Data Index: 6668343 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9098. Min Range: -7.9098
Max Act: 7.3786. Min Act: -0.1700
Data Index: 4005251 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9098. Min Range: -7.9098
Max Act: 7.3786. Min Act: -0.1700
Data Index: 6405165 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9098. Min Range: -7.9098
Max Act: 7.3473. Min Act: -0.1700
Data Index: 5370966 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9098. Min Range: -7.9098
Max Act: 7.3786. Min Act: -0.1700
Data Index: 4261092 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9098. Min Range: -7.9098
Max Act: 7.3473. Min Act: -0.1700
Data Index: 7321778 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9098. Min Range: -7.9098
Max Act: 7.3473. Min Act: -0.1700
Data Index: 6726089 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9098. Min Range: -7.9098
Max Act: 7.3473. Min Act: -0.1700
Data Index: 3783371 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #19