Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2064 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6674. Min Range: -5.6674
Max Act: 5.6674. Min Act: -0.1700
Data Index: 7792915 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6674. Min Range: -5.6674
Max Act: 5.6674. Min Act: -0.1700
Data Index: 1363374 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6674. Min Range: -5.6674
Max Act: 5.5424. Min Act: -0.1700
Data Index: 7862879 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6674. Min Range: -5.6674
Max Act: 5.5111. Min Act: -0.1700
Data Index: 1237661 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6674. Min Range: -5.6674
Max Act: 5.5424. Min Act: -0.1700
Data Index: 7443470 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6674. Min Range: -5.6674
Max Act: 5.5111. Min Act: -0.1700
Data Index: 2217540 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6674. Min Range: -5.6674
Max Act: 5.5111. Min Act: -0.1700
Data Index: 1738193 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6674. Min Range: -5.6674
Max Act: 5.5111. Min Act: -0.1700
Data Index: 6528110 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6674. Min Range: -5.6674
Max Act: 5.4799. Min Act: -0.1700
Data Index: 3066358 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6674. Min Range: -5.6674
Max Act: 5.4486. Min Act: -0.1700
Data Index: 1138881 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6674. Min Range: -5.6674
Max Act: 5.3861. Min Act: -0.1700
Data Index: 7050816 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6674. Min Range: -5.6674
Max Act: 5.3861. Min Act: -0.1700
Data Index: 5917720 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6674. Min Range: -5.6674
Max Act: 5.3549. Min Act: -0.1700
Data Index: 4834553 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6674. Min Range: -5.6674
Max Act: 5.3236. Min Act: -0.1700
Data Index: 8108993 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6674. Min Range: -5.6674
Max Act: 5.3236. Min Act: -0.1700
Data Index: 2997671 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6674. Min Range: -5.6674
Max Act: 5.2611. Min Act: -0.1700
Data Index: 6037808 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6674. Min Range: -5.6674
Max Act: 5.2924. Min Act: -0.1700
Data Index: 527351 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6674. Min Range: -5.6674
Max Act: 5.2924. Min Act: -0.1700
Data Index: 7160980 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6674. Min Range: -5.6674
Max Act: 5.2924. Min Act: -0.1700
Data Index: 4007847 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6674. Min Range: -5.6674
Max Act: 5.2611. Min Act: -0.1700
Data Index: 6355522 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #19