Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4898 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.0108. Min Range: -7.0108
Max Act: 7.0108. Min Act: -0.1700
Data Index: 7678896 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0108. Min Range: -7.0108
Max Act: 7.0108. Min Act: -0.1700
Data Index: 3272122 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0108. Min Range: -7.0108
Max Act: 7.0108. Min Act: -0.1700
Data Index: 5528962 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0108. Min Range: -7.0108
Max Act: 6.9483. Min Act: -0.1700
Data Index: 3025475 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0108. Min Range: -7.0108
Max Act: 6.8858. Min Act: -0.1700
Data Index: 4233999 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0108. Min Range: -7.0108
Max Act: 6.8545. Min Act: -0.1700
Data Index: 7670256 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0108. Min Range: -7.0108
Max Act: 6.8233. Min Act: -0.1700
Data Index: 6449816 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0108. Min Range: -7.0108
Max Act: 6.7920. Min Act: -0.1700
Data Index: 7087877 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0108. Min Range: -7.0108
Max Act: 6.7608. Min Act: -0.1700
Data Index: 3448190 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0108. Min Range: -7.0108
Max Act: 6.8233. Min Act: -0.1700
Data Index: 5882772 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0108. Min Range: -7.0108
Max Act: 6.7608. Min Act: -0.1700
Data Index: 6119398 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0108. Min Range: -7.0108
Max Act: 6.7608. Min Act: -0.1700
Data Index: 6319146 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0108. Min Range: -7.0108
Max Act: 6.7295. Min Act: -0.1700
Data Index: 2263119 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0108. Min Range: -7.0108
Max Act: 6.7295. Min Act: -0.1700
Data Index: 5937124 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0108. Min Range: -7.0108
Max Act: 6.7295. Min Act: -0.1700
Data Index: 4021051 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0108. Min Range: -7.0108
Max Act: 6.6670. Min Act: -0.1700
Data Index: 3741414 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0108. Min Range: -7.0108
Max Act: 6.6670. Min Act: -0.1700
Data Index: 3580994 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0108. Min Range: -7.0108
Max Act: 6.6983. Min Act: -0.1700
Data Index: 199625 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0108. Min Range: -7.0108
Max Act: 6.6358. Min Act: -0.1700
Data Index: 1099014 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0108. Min Range: -7.0108
Max Act: 6.6358. Min Act: -0.1700
Data Index: 5303101 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #19