Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4909 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9463. Min Range: -7.9463
Max Act: 7.9463. Min Act: -0.1700
Data Index: 4563641 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9463. Min Range: -7.9463
Max Act: 7.8838. Min Act: -0.1700
Data Index: 1869456 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9463. Min Range: -7.9463
Max Act: 7.8526. Min Act: -0.1700
Data Index: 1090282 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9463. Min Range: -7.9463
Max Act: 7.6026. Min Act: -0.1700
Data Index: 7328897 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9463. Min Range: -7.9463
Max Act: 7.5713. Min Act: -0.1700
Data Index: 1951790 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9463. Min Range: -7.9463
Max Act: 7.5713. Min Act: -0.1700
Data Index: 3677661 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9463. Min Range: -7.9463
Max Act: 7.5401. Min Act: -0.1700
Data Index: 3752907 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9463. Min Range: -7.9463
Max Act: 7.4776. Min Act: -0.1700
Data Index: 1126203 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9463. Min Range: -7.9463
Max Act: 7.4776. Min Act: -0.1700
Data Index: 1027226 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9463. Min Range: -7.9463
Max Act: 7.3213. Min Act: -0.1700
Data Index: 7867461 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9463. Min Range: -7.9463
Max Act: 7.3213. Min Act: -0.1700
Data Index: 590593 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9463. Min Range: -7.9463
Max Act: 7.2901. Min Act: -0.1700
Data Index: 2444317 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9463. Min Range: -7.9463
Max Act: 7.2901. Min Act: -0.1700
Data Index: 8509935 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9463. Min Range: -7.9463
Max Act: 7.2276. Min Act: -0.1700
Data Index: 3775196 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9463. Min Range: -7.9463
Max Act: 7.1963. Min Act: -0.1700
Data Index: 1063337 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9463. Min Range: -7.9463
Max Act: 7.1963. Min Act: -0.1700
Data Index: 7139007 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9463. Min Range: -7.9463
Max Act: 7.1963. Min Act: -0.1700
Data Index: 6009863 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9463. Min Range: -7.9463
Max Act: 7.1651. Min Act: -0.1700
Data Index: 1403482 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9463. Min Range: -7.9463
Max Act: 7.1651. Min Act: -0.1700
Data Index: 8712347 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9463. Min Range: -7.9463
Max Act: 7.1338. Min Act: -0.1700
Data Index: 134529 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #19