Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5709 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0769. Min Range: -6.0769
Max Act: 6.0457. Min Act: -0.1700
Data Index: 3194763 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0769. Min Range: -6.0769
Max Act: 6.0769. Min Act: -0.1700
Data Index: 192804 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0769. Min Range: -6.0769
Max Act: 6.0144. Min Act: -0.1700
Data Index: 8213175 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0769. Min Range: -6.0769
Max Act: 5.9832. Min Act: -0.1700
Data Index: 2394165 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0769. Min Range: -6.0769
Max Act: 5.9207. Min Act: -0.1700
Data Index: 6314266 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0769. Min Range: -6.0769
Max Act: 5.9207. Min Act: -0.1700
Data Index: 5644527 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0769. Min Range: -6.0769
Max Act: 5.9207. Min Act: -0.1700
Data Index: 6613621 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0769. Min Range: -6.0769
Max Act: 5.9207. Min Act: -0.1700
Data Index: 6157324 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0769. Min Range: -6.0769
Max Act: 5.8894. Min Act: -0.1700
Data Index: 2064710 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0769. Min Range: -6.0769
Max Act: 5.8269. Min Act: -0.1700
Data Index: 3745140 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0769. Min Range: -6.0769
Max Act: 5.8269. Min Act: -0.1700
Data Index: 6530052 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0769. Min Range: -6.0769
Max Act: 5.8269. Min Act: -0.1700
Data Index: 5231066 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0769. Min Range: -6.0769
Max Act: 5.8269. Min Act: -0.1700
Data Index: 7886346 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0769. Min Range: -6.0769
Max Act: 5.8269. Min Act: -0.1700
Data Index: 7796238 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0769. Min Range: -6.0769
Max Act: 5.8269. Min Act: -0.1700
Data Index: 8511597 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0769. Min Range: -6.0769
Max Act: 5.8269. Min Act: -0.1700
Data Index: 7760058 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0769. Min Range: -6.0769
Max Act: 5.7957. Min Act: -0.1700
Data Index: 7926923 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0769. Min Range: -6.0769
Max Act: 5.7957. Min Act: -0.1700
Data Index: 1748023 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0769. Min Range: -6.0769
Max Act: 5.7957. Min Act: -0.1700
Data Index: 1899371 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0769. Min Range: -6.0769
Max Act: 5.7957. Min Act: -0.1700
Data Index: 4869622 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #19