Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2104 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7273. Min Range: -5.7273
Max Act: 5.7273. Min Act: -0.1700
Data Index: 2656958 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7273. Min Range: -5.7273
Max Act: 5.5711. Min Act: -0.1700
Data Index: 1580020 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7273. Min Range: -5.7273
Max Act: 5.5711. Min Act: -0.1700
Data Index: 6097331 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7273. Min Range: -5.7273
Max Act: 5.5398. Min Act: -0.1700
Data Index: 6205878 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7273. Min Range: -5.7273
Max Act: 5.4461. Min Act: -0.1700
Data Index: 6021435 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7273. Min Range: -5.7273
Max Act: 5.3836. Min Act: -0.1700
Data Index: 3592510 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7273. Min Range: -5.7273
Max Act: 5.3523. Min Act: -0.1700
Data Index: 2094131 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7273. Min Range: -5.7273
Max Act: 5.3211. Min Act: -0.1700
Data Index: 7121318 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7273. Min Range: -5.7273
Max Act: 5.3211. Min Act: -0.1700
Data Index: 4014883 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7273. Min Range: -5.7273
Max Act: 5.3211. Min Act: -0.1700
Data Index: 8669130 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7273. Min Range: -5.7273
Max Act: 5.2898. Min Act: -0.1700
Data Index: 332992 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7273. Min Range: -5.7273
Max Act: 5.2586. Min Act: -0.1700
Data Index: 5118072 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7273. Min Range: -5.7273
Max Act: 5.2586. Min Act: -0.1700
Data Index: 2676914 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7273. Min Range: -5.7273
Max Act: 5.2273. Min Act: -0.1700
Data Index: 6020469 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7273. Min Range: -5.7273
Max Act: 5.2273. Min Act: -0.1700
Data Index: 1289435 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7273. Min Range: -5.7273
Max Act: 5.1961. Min Act: -0.1700
Data Index: 242995 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7273. Min Range: -5.7273
Max Act: 5.2273. Min Act: -0.1700
Data Index: 2903271 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7273. Min Range: -5.7273
Max Act: 5.1961. Min Act: -0.1700
Data Index: 4389345 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7273. Min Range: -5.7273
Max Act: 5.2273. Min Act: -0.1700
Data Index: 2851985 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7273. Min Range: -5.7273
Max Act: 5.1648. Min Act: -0.1700
Data Index: 6357224 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #19