Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3103 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1354. Min Range: -10.1354
Max Act: 10.1354. Min Act: -0.1700
Data Index: 7937060 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1354. Min Range: -10.1354
Max Act: 10.1354. Min Act: -0.1700
Data Index: 7046076 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1354. Min Range: -10.1354
Max Act: 10.0729. Min Act: -0.1700
Data Index: 6755717 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1354. Min Range: -10.1354
Max Act: 9.9479. Min Act: -0.1700
Data Index: 506532 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1354. Min Range: -10.1354
Max Act: 9.9479. Min Act: -0.1700
Data Index: 5648508 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1354. Min Range: -10.1354
Max Act: 9.8854. Min Act: -0.1700
Data Index: 1857199 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1354. Min Range: -10.1354
Max Act: 9.8229. Min Act: -0.1700
Data Index: 3464804 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1354. Min Range: -10.1354
Max Act: 9.8229. Min Act: -0.1700
Data Index: 5106664 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1354. Min Range: -10.1354
Max Act: 9.8229. Min Act: -0.1700
Data Index: 4286873 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1354. Min Range: -10.1354
Max Act: 9.8229. Min Act: -0.1700
Data Index: 5665728 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1354. Min Range: -10.1354
Max Act: 9.7604. Min Act: -0.1700
Data Index: 2844770 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1354. Min Range: -10.1354
Max Act: 9.7604. Min Act: -0.1700
Data Index: 7382421 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1354. Min Range: -10.1354
Max Act: 9.7604. Min Act: -0.1700
Data Index: 2813036 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1354. Min Range: -10.1354
Max Act: 9.7604. Min Act: -0.1700
Data Index: 597206 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1354. Min Range: -10.1354
Max Act: 9.7604. Min Act: -0.1700
Data Index: 5278783 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1354. Min Range: -10.1354
Max Act: 9.7604. Min Act: -0.1700
Data Index: 690709 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1354. Min Range: -10.1354
Max Act: 9.7604. Min Act: -0.1700
Data Index: 7153259 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1354. Min Range: -10.1354
Max Act: 9.6979. Min Act: -0.1700
Data Index: 49131 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1354. Min Range: -10.1354
Max Act: 9.6979. Min Act: -0.1700
Data Index: 928379 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1354. Min Range: -10.1354
Max Act: 9.6979. Min Act: -0.1700
Data Index: 339749 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #19