Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3587 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7312. Min Range: -8.7312
Max Act: 8.7312. Min Act: -0.1700
Data Index: 8557384 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7312. Min Range: -8.7312
Max Act: 8.6062. Min Act: -0.1700
Data Index: 1722198 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7312. Min Range: -8.7312
Max Act: 8.5437. Min Act: -0.1700
Data Index: 4483940 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7312. Min Range: -8.7312
Max Act: 8.3562. Min Act: -0.1700
Data Index: 7659491 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7312. Min Range: -8.7312
Max Act: 8.2937. Min Act: -0.1700
Data Index: 7198024 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7312. Min Range: -8.7312
Max Act: 8.1687. Min Act: -0.1700
Data Index: 5548145 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7312. Min Range: -8.7312
Max Act: 8.2312. Min Act: -0.1700
Data Index: 7188992 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7312. Min Range: -8.7312
Max Act: 8.1062. Min Act: -0.1700
Data Index: 4805874 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7312. Min Range: -8.7312
Max Act: 8.0437. Min Act: -0.1700
Data Index: 5414562 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7312. Min Range: -8.7312
Max Act: 7.9187. Min Act: -0.1700
Data Index: 4483941 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7312. Min Range: -8.7312
Max Act: 7.9812. Min Act: -0.1700
Data Index: 748433 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7312. Min Range: -8.7312
Max Act: 7.9187. Min Act: -0.1700
Data Index: 4171459 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7312. Min Range: -8.7312
Max Act: 7.9187. Min Act: -0.1700
Data Index: 1954019 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7312. Min Range: -8.7312
Max Act: 7.9187. Min Act: -0.1700
Data Index: 4171456 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7312. Min Range: -8.7312
Max Act: 7.8562. Min Act: -0.1700
Data Index: 1703326 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7312. Min Range: -8.7312
Max Act: 7.7937. Min Act: -0.1700
Data Index: 2407094 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7312. Min Range: -8.7312
Max Act: 7.7937. Min Act: -0.1700
Data Index: 5295775 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7312. Min Range: -8.7312
Max Act: 7.7937. Min Act: -0.1700
Data Index: 4171457 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7312. Min Range: -8.7312
Max Act: 7.7312. Min Act: -0.1700
Data Index: 4219572 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7312. Min Range: -8.7312
Max Act: 7.6687. Min Act: -0.1700
Data Index: 1100957 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #19