Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1520 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0471. Min Range: -5.0471
Max Act: 5.0471. Min Act: -0.1700
Data Index: 6765128 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0471. Min Range: -5.0471
Max Act: 4.9221. Min Act: -0.1700
Data Index: 4924395 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0471. Min Range: -5.0471
Max Act: 4.8284. Min Act: -0.1700
Data Index: 6979486 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0471. Min Range: -5.0471
Max Act: 4.7034. Min Act: -0.1700
Data Index: 3764112 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0471. Min Range: -5.0471
Max Act: 4.6721. Min Act: -0.1700
Data Index: 667750 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0471. Min Range: -5.0471
Max Act: 4.6409. Min Act: -0.1700
Data Index: 6765127 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0471. Min Range: -5.0471
Max Act: 4.6409. Min Act: -0.1700
Data Index: 4081895 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0471. Min Range: -5.0471
Max Act: 4.6409. Min Act: -0.1700
Data Index: 440105 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0471. Min Range: -5.0471
Max Act: 4.5783. Min Act: -0.1700
Data Index: 6765123 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0471. Min Range: -5.0471
Max Act: 4.5471. Min Act: -0.1700
Data Index: 7441163 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0471. Min Range: -5.0471
Max Act: 4.5158. Min Act: -0.1700
Data Index: 2312353 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0471. Min Range: -5.0471
Max Act: 4.4221. Min Act: -0.1700
Data Index: 1163616 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0471. Min Range: -5.0471
Max Act: 4.4221. Min Act: -0.1700
Data Index: 6203661 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0471. Min Range: -5.0471
Max Act: 4.3908. Min Act: -0.1700
Data Index: 938036 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0471. Min Range: -5.0471
Max Act: 4.3908. Min Act: -0.1700
Data Index: 4124402 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0471. Min Range: -5.0471
Max Act: 4.3283. Min Act: -0.1700
Data Index: 8362512 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0471. Min Range: -5.0471
Max Act: 4.3283. Min Act: -0.1700
Data Index: 5042302 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0471. Min Range: -5.0471
Max Act: 4.2971. Min Act: -0.1700
Data Index: 7672815 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0471. Min Range: -5.0471
Max Act: 4.2658. Min Act: -0.1700
Data Index: 7410135 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0471. Min Range: -5.0471
Max Act: 4.2658. Min Act: -0.1700
Data Index: 5202296 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #19