Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4540 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0340. Min Range: -8.0340
Max Act: 8.0340. Min Act: -0.1700
Data Index: 1443531 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0340. Min Range: -8.0340
Max Act: 8.0340. Min Act: -0.1700
Data Index: 1443518 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0340. Min Range: -8.0340
Max Act: 7.9090. Min Act: -0.1700
Data Index: 8653829 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0340. Min Range: -8.0340
Max Act: 7.9090. Min Act: -0.1700
Data Index: 3342716 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0340. Min Range: -8.0340
Max Act: 7.7840. Min Act: -0.1700
Data Index: 5742726 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0340. Min Range: -8.0340
Max Act: 7.7215. Min Act: -0.1700
Data Index: 6927464 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0340. Min Range: -8.0340
Max Act: 7.7215. Min Act: -0.1700
Data Index: 6265105 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0340. Min Range: -8.0340
Max Act: 7.6903. Min Act: -0.1700
Data Index: 2697421 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0340. Min Range: -8.0340
Max Act: 7.6278. Min Act: -0.1700
Data Index: 4151437 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0340. Min Range: -8.0340
Max Act: 7.6278. Min Act: -0.1700
Data Index: 7165404 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0340. Min Range: -8.0340
Max Act: 7.5965. Min Act: -0.1700
Data Index: 8257205 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0340. Min Range: -8.0340
Max Act: 7.5340. Min Act: -0.1700
Data Index: 927462 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0340. Min Range: -8.0340
Max Act: 7.5653. Min Act: -0.1700
Data Index: 5742725 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0340. Min Range: -8.0340
Max Act: 7.5028. Min Act: -0.1700
Data Index: 5308337 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0340. Min Range: -8.0340
Max Act: 7.5028. Min Act: -0.1700
Data Index: 8593656 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0340. Min Range: -8.0340
Max Act: 7.5028. Min Act: -0.1700
Data Index: 8128932 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0340. Min Range: -8.0340
Max Act: 7.4403. Min Act: -0.1700
Data Index: 8710946 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0340. Min Range: -8.0340
Max Act: 7.5028. Min Act: -0.1700
Data Index: 8128946 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0340. Min Range: -8.0340
Max Act: 7.4403. Min Act: -0.1700
Data Index: 7165414 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0340. Min Range: -8.0340
Max Act: 7.4090. Min Act: -0.1700
Data Index: 8691642 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #19