Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1176 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.5659. Min Range: -10.5659
Max Act: 10.5659. Min Act: -0.1700
Data Index: 5626190 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5659. Min Range: -10.5659
Max Act: 10.3784. Min Act: -0.1700
Data Index: 5636538 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5659. Min Range: -10.5659
Max Act: 10.3159. Min Act: -0.1700
Data Index: 8371094 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5659. Min Range: -10.5659
Max Act: 10.1909. Min Act: -0.1700
Data Index: 6151072 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5659. Min Range: -10.5659
Max Act: 10.1909. Min Act: -0.1700
Data Index: 3513800 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5659. Min Range: -10.5659
Max Act: 10.1909. Min Act: -0.1700
Data Index: 7821297 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5659. Min Range: -10.5659
Max Act: 10.1909. Min Act: -0.1700
Data Index: 800538 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5659. Min Range: -10.5659
Max Act: 10.1284. Min Act: -0.1700
Data Index: 3015230 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5659. Min Range: -10.5659
Max Act: 10.0659. Min Act: -0.1700
Data Index: 5181116 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5659. Min Range: -10.5659
Max Act: 9.9409. Min Act: -0.1700
Data Index: 665399 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5659. Min Range: -10.5659
Max Act: 10.0034. Min Act: -0.1700
Data Index: 2541711 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5659. Min Range: -10.5659
Max Act: 9.9409. Min Act: -0.1700
Data Index: 4707812 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5659. Min Range: -10.5659
Max Act: 9.8784. Min Act: -0.1700
Data Index: 8452901 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5659. Min Range: -10.5659
Max Act: 9.8784. Min Act: -0.1700
Data Index: 4165532 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5659. Min Range: -10.5659
Max Act: 9.8784. Min Act: -0.1700
Data Index: 3866372 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5659. Min Range: -10.5659
Max Act: 9.8784. Min Act: -0.1700
Data Index: 2255818 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5659. Min Range: -10.5659
Max Act: 9.8159. Min Act: -0.1700
Data Index: 6006101 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5659. Min Range: -10.5659
Max Act: 9.8159. Min Act: -0.1700
Data Index: 2922858 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5659. Min Range: -10.5659
Max Act: 9.8159. Min Act: -0.1700
Data Index: 3999175 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5659. Min Range: -10.5659
Max Act: 9.8159. Min Act: -0.1700
Data Index: 2083299 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #19