Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4278 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4365. Min Range: -3.4365
Max Act: 3.4365. Min Act: -0.1700
Data Index: 1644664 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4365. Min Range: -3.4365
Max Act: 3.2797. Min Act: -0.1690
Data Index: 5533403 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4365. Min Range: -3.4365
Max Act: 3.2797. Min Act: -0.1672
Data Index: 7099265 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4365. Min Range: -3.4365
Max Act: 3.2797. Min Act: -0.1693
Data Index: 3453027 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4365. Min Range: -3.4365
Max Act: 3.2797. Min Act: -0.1700
Data Index: 4386836 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4365. Min Range: -3.4365
Max Act: 3.2797. Min Act: -0.1700
Data Index: 3717551 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4365. Min Range: -3.4365
Max Act: 3.2482. Min Act: -0.1690
Data Index: 3336743 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4365. Min Range: -3.4365
Max Act: 3.2797. Min Act: -0.1699
Data Index: 1369247 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4365. Min Range: -3.4365
Max Act: 3.2482. Min Act: -0.1699
Data Index: 7780217 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4365. Min Range: -3.4365
Max Act: 3.2168. Min Act: -0.1699
Data Index: 7892816 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4365. Min Range: -3.4365
Max Act: 3.2168. Min Act: -0.1670
Data Index: 6393069 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4365. Min Range: -3.4365
Max Act: 3.2168. Min Act: -0.1699
Data Index: 3217612 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4365. Min Range: -3.4365
Max Act: 3.2482. Min Act: -0.1647
Data Index: 7099268 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4365. Min Range: -3.4365
Max Act: 3.1854. Min Act: -0.1670
Data Index: 8212991 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4365. Min Range: -3.4365
Max Act: 3.1854. Min Act: -0.1647
Data Index: 6469446 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4365. Min Range: -3.4365
Max Act: 3.1854. Min Act: -0.1700
Data Index: 2093855 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4365. Min Range: -3.4365
Max Act: 3.1539. Min Act: -0.1647
Data Index: 3703773 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4365. Min Range: -3.4365
Max Act: 3.1539. Min Act: -0.1694
Data Index: 3583905 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4365. Min Range: -3.4365
Max Act: 3.1854. Min Act: -0.1690
Data Index: 548446 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4365. Min Range: -3.4365
Max Act: 3.1539. Min Act: -0.1665
Data Index: 1315338 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #19