Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2704 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4205. Min Range: -8.4205
Max Act: 8.4205. Min Act: -0.1700
Data Index: 6169865 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4205. Min Range: -8.4205
Max Act: 8.0455. Min Act: -0.1700
Data Index: 2557302 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4205. Min Range: -8.4205
Max Act: 7.9830. Min Act: -0.1700
Data Index: 8729315 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4205. Min Range: -8.4205
Max Act: 7.9830. Min Act: -0.1700
Data Index: 2304092 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4205. Min Range: -8.4205
Max Act: 7.8580. Min Act: -0.1700
Data Index: 7464114 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4205. Min Range: -8.4205
Max Act: 7.8580. Min Act: -0.1700
Data Index: 1986459 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4205. Min Range: -8.4205
Max Act: 7.8580. Min Act: -0.1700
Data Index: 5034749 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4205. Min Range: -8.4205
Max Act: 7.8267. Min Act: -0.1700
Data Index: 7742490 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4205. Min Range: -8.4205
Max Act: 7.7955. Min Act: -0.1700
Data Index: 5946550 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4205. Min Range: -8.4205
Max Act: 7.7642. Min Act: -0.1700
Data Index: 1803963 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4205. Min Range: -8.4205
Max Act: 7.7330. Min Act: -0.1700
Data Index: 3331891 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4205. Min Range: -8.4205
Max Act: 7.7330. Min Act: -0.1700
Data Index: 5146085 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4205. Min Range: -8.4205
Max Act: 7.6705. Min Act: -0.1700
Data Index: 3869167 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4205. Min Range: -8.4205
Max Act: 7.6705. Min Act: -0.1700
Data Index: 37344 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4205. Min Range: -8.4205
Max Act: 7.6705. Min Act: -0.1700
Data Index: 8663868 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4205. Min Range: -8.4205
Max Act: 7.7017. Min Act: -0.1700
Data Index: 6375709 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4205. Min Range: -8.4205
Max Act: 7.6705. Min Act: -0.1700
Data Index: 7258587 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4205. Min Range: -8.4205
Max Act: 7.6392. Min Act: -0.1700
Data Index: 134221 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4205. Min Range: -8.4205
Max Act: 7.6392. Min Act: -0.1700
Data Index: 6246971 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4205. Min Range: -8.4205
Max Act: 7.6080. Min Act: -0.1700
Data Index: 952714 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #19