Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3260 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6749. Min Range: -6.6749
Max Act: 6.6749. Min Act: -0.1700
Data Index: 1664222 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6749. Min Range: -6.6749
Max Act: 6.6124. Min Act: -0.1700
Data Index: 5954579 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6749. Min Range: -6.6749
Max Act: 6.5186. Min Act: -0.1700
Data Index: 4184289 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6749. Min Range: -6.6749
Max Act: 6.2999. Min Act: -0.1700
Data Index: 7195025 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6749. Min Range: -6.6749
Max Act: 6.0499. Min Act: -0.1700
Data Index: 2376607 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6749. Min Range: -6.6749
Max Act: 6.0499. Min Act: -0.1700
Data Index: 480691 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6749. Min Range: -6.6749
Max Act: 5.9561. Min Act: -0.1700
Data Index: 6790468 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6749. Min Range: -6.6749
Max Act: 5.8624. Min Act: -0.1700
Data Index: 7126712 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6749. Min Range: -6.6749
Max Act: 5.8936. Min Act: -0.1700
Data Index: 5075256 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6749. Min Range: -6.6749
Max Act: 5.8624. Min Act: -0.1700
Data Index: 8829094 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6749. Min Range: -6.6749
Max Act: 5.8311. Min Act: -0.1700
Data Index: 4184290 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6749. Min Range: -6.6749
Max Act: 5.8311. Min Act: -0.1700
Data Index: 2891914 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6749. Min Range: -6.6749
Max Act: 5.8311. Min Act: -0.1700
Data Index: 6844884 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6749. Min Range: -6.6749
Max Act: 5.7999. Min Act: -0.1700
Data Index: 6322571 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6749. Min Range: -6.6749
Max Act: 5.7686. Min Act: -0.1700
Data Index: 3483267 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6749. Min Range: -6.6749
Max Act: 5.7374. Min Act: -0.1700
Data Index: 1584072 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6749. Min Range: -6.6749
Max Act: 5.7686. Min Act: -0.1700
Data Index: 7862608 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6749. Min Range: -6.6749
Max Act: 5.7686. Min Act: -0.1700
Data Index: 1019346 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6749. Min Range: -6.6749
Max Act: 5.7686. Min Act: -0.1700
Data Index: 5483715 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6749. Min Range: -6.6749
Max Act: 5.7686. Min Act: -0.1700
Data Index: 5842658 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #19