Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1707 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5295. Min Range: -6.5295
Max Act: 6.5295. Min Act: -0.1700
Data Index: 3583917 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5295. Min Range: -6.5295
Max Act: 6.2795. Min Act: -0.1700
Data Index: 6348764 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5295. Min Range: -6.5295
Max Act: 6.1233. Min Act: -0.1700
Data Index: 1947398 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5295. Min Range: -6.5295
Max Act: 6.0920. Min Act: -0.1700
Data Index: 1560859 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5295. Min Range: -6.5295
Max Act: 6.0608. Min Act: -0.1700
Data Index: 1595139 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5295. Min Range: -6.5295
Max Act: 6.0608. Min Act: -0.1700
Data Index: 5905654 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5295. Min Range: -6.5295
Max Act: 6.0295. Min Act: -0.1700
Data Index: 2478383 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5295. Min Range: -6.5295
Max Act: 6.0295. Min Act: -0.1700
Data Index: 5770500 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5295. Min Range: -6.5295
Max Act: 5.9983. Min Act: -0.1700
Data Index: 1115761 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5295. Min Range: -6.5295
Max Act: 5.9983. Min Act: -0.1700
Data Index: 5630721 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5295. Min Range: -6.5295
Max Act: 5.9670. Min Act: -0.1700
Data Index: 2787591 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5295. Min Range: -6.5295
Max Act: 5.9983. Min Act: -0.1700
Data Index: 8456198 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5295. Min Range: -6.5295
Max Act: 5.9670. Min Act: -0.1700
Data Index: 2866458 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5295. Min Range: -6.5295
Max Act: 5.9358. Min Act: -0.1700
Data Index: 3538421 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5295. Min Range: -6.5295
Max Act: 5.9358. Min Act: -0.1700
Data Index: 5345740 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5295. Min Range: -6.5295
Max Act: 5.9358. Min Act: -0.1700
Data Index: 6991933 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5295. Min Range: -6.5295
Max Act: 5.9358. Min Act: -0.1700
Data Index: 1440847 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5295. Min Range: -6.5295
Max Act: 5.9358. Min Act: -0.1700
Data Index: 4594178 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5295. Min Range: -6.5295
Max Act: 5.9045. Min Act: -0.1700
Data Index: 4364094 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5295. Min Range: -6.5295
Max Act: 5.9045. Min Act: -0.1700
Data Index: 8213065 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #19