Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5908 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3960. Min Range: -8.3960
Max Act: 8.3960. Min Act: -0.1700
Data Index: 8021893 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3960. Min Range: -8.3960
Max Act: 8.2710. Min Act: -0.1700
Data Index: 5250553 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3960. Min Range: -8.3960
Max Act: 8.1460. Min Act: -0.1700
Data Index: 275017 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3960. Min Range: -8.3960
Max Act: 8.1460. Min Act: -0.1700
Data Index: 6256107 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3960. Min Range: -8.3960
Max Act: 8.0835. Min Act: -0.1700
Data Index: 423686 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3960. Min Range: -8.3960
Max Act: 7.8960. Min Act: -0.1700
Data Index: 1112399 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3960. Min Range: -8.3960
Max Act: 7.7398. Min Act: -0.1700
Data Index: 5887597 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3960. Min Range: -8.3960
Max Act: 7.7398. Min Act: -0.1700
Data Index: 2947378 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3960. Min Range: -8.3960
Max Act: 7.7085. Min Act: -0.1700
Data Index: 1133396 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3960. Min Range: -8.3960
Max Act: 7.7085. Min Act: -0.1700
Data Index: 78696 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3960. Min Range: -8.3960
Max Act: 7.6460. Min Act: -0.1700
Data Index: 8025876 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3960. Min Range: -8.3960
Max Act: 7.6773. Min Act: -0.1700
Data Index: 6559285 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3960. Min Range: -8.3960
Max Act: 7.6460. Min Act: -0.1700
Data Index: 1974876 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3960. Min Range: -8.3960
Max Act: 7.6148. Min Act: -0.1700
Data Index: 5182755 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3960. Min Range: -8.3960
Max Act: 7.6148. Min Act: -0.1700
Data Index: 285061 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3960. Min Range: -8.3960
Max Act: 7.5835. Min Act: -0.1700
Data Index: 396077 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3960. Min Range: -8.3960
Max Act: 7.5835. Min Act: -0.1700
Data Index: 6477476 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3960. Min Range: -8.3960
Max Act: 7.4898. Min Act: -0.1700
Data Index: 4309444 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3960. Min Range: -8.3960
Max Act: 7.4898. Min Act: -0.1700
Data Index: 5930093 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3960. Min Range: -8.3960
Max Act: 7.4898. Min Act: -0.1700
Data Index: 6439306 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #19