Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2868 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9832. Min Range: -5.9832
Max Act: 5.9832. Min Act: -0.1700
Data Index: 8312246 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9832. Min Range: -5.9832
Max Act: 5.8895. Min Act: -0.1700
Data Index: 6453221 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9832. Min Range: -5.9832
Max Act: 5.8582. Min Act: -0.1700
Data Index: 7277912 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9832. Min Range: -5.9832
Max Act: 5.8582. Min Act: -0.1700
Data Index: 5226539 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9832. Min Range: -5.9832
Max Act: 5.8270. Min Act: -0.1700
Data Index: 449131 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9832. Min Range: -5.9832
Max Act: 5.8582. Min Act: -0.1700
Data Index: 686213 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9832. Min Range: -5.9832
Max Act: 5.8270. Min Act: -0.1700
Data Index: 2312978 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9832. Min Range: -5.9832
Max Act: 5.8270. Min Act: -0.1700
Data Index: 7426072 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9832. Min Range: -5.9832
Max Act: 5.7645. Min Act: -0.1700
Data Index: 2864286 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9832. Min Range: -5.9832
Max Act: 5.7332. Min Act: -0.1700
Data Index: 4192810 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9832. Min Range: -5.9832
Max Act: 5.6395. Min Act: -0.1700
Data Index: 3397757 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9832. Min Range: -5.9832
Max Act: 5.6707. Min Act: -0.1700
Data Index: 7682586 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9832. Min Range: -5.9832
Max Act: 5.6395. Min Act: -0.1700
Data Index: 6938202 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9832. Min Range: -5.9832
Max Act: 5.6395. Min Act: -0.1700
Data Index: 5766305 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9832. Min Range: -5.9832
Max Act: 5.6395. Min Act: -0.1700
Data Index: 850720 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9832. Min Range: -5.9832
Max Act: 5.5770. Min Act: -0.1700
Data Index: 7639579 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9832. Min Range: -5.9832
Max Act: 5.6395. Min Act: -0.1700
Data Index: 2841004 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9832. Min Range: -5.9832
Max Act: 5.6082. Min Act: -0.1700
Data Index: 2966419 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9832. Min Range: -5.9832
Max Act: 5.5770. Min Act: -0.1700
Data Index: 6107022 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9832. Min Range: -5.9832
Max Act: 5.5770. Min Act: -0.1700
Data Index: 7822612 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #19