Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2461 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1670. Min Range: -6.1670
Max Act: 6.1670. Min Act: -0.1700
Data Index: 6105611 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1670. Min Range: -6.1670
Max Act: 5.9482. Min Act: -0.1700
Data Index: 6433863 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1670. Min Range: -6.1670
Max Act: 5.8545. Min Act: -0.1700
Data Index: 4698053 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1670. Min Range: -6.1670
Max Act: 5.8232. Min Act: -0.1700
Data Index: 6463291 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1670. Min Range: -6.1670
Max Act: 5.7920. Min Act: -0.1700
Data Index: 7109143 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1670. Min Range: -6.1670
Max Act: 5.7920. Min Act: -0.1700
Data Index: 493812 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1670. Min Range: -6.1670
Max Act: 5.7920. Min Act: -0.1700
Data Index: 2826530 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1670. Min Range: -6.1670
Max Act: 5.7607. Min Act: -0.1700
Data Index: 1827868 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1670. Min Range: -6.1670
Max Act: 5.7607. Min Act: -0.1700
Data Index: 6407841 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1670. Min Range: -6.1670
Max Act: 5.7295. Min Act: -0.1700
Data Index: 4764249 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1670. Min Range: -6.1670
Max Act: 5.6982. Min Act: -0.1700
Data Index: 111545 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1670. Min Range: -6.1670
Max Act: 5.6982. Min Act: -0.1700
Data Index: 2242438 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1670. Min Range: -6.1670
Max Act: 5.6982. Min Act: -0.1700
Data Index: 7121980 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1670. Min Range: -6.1670
Max Act: 5.6670. Min Act: -0.1700
Data Index: 846816 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1670. Min Range: -6.1670
Max Act: 5.6670. Min Act: -0.1700
Data Index: 6647509 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1670. Min Range: -6.1670
Max Act: 5.6670. Min Act: -0.1700
Data Index: 7348167 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1670. Min Range: -6.1670
Max Act: 5.6670. Min Act: -0.1700
Data Index: 7205060 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1670. Min Range: -6.1670
Max Act: 5.6670. Min Act: -0.1700
Data Index: 840830 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1670. Min Range: -6.1670
Max Act: 5.6670. Min Act: -0.1700
Data Index: 5355724 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1670. Min Range: -6.1670
Max Act: 5.6670. Min Act: -0.1700
Data Index: 8424434 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #19