Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 38 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5502. Min Range: -4.5502
Max Act: 4.5502. Min Act: -0.1700
Data Index: 7332826 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5502. Min Range: -4.5502
Max Act: 4.5190. Min Act: -0.1700
Data Index: 5716541 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5502. Min Range: -4.5502
Max Act: 4.5190. Min Act: -0.1700
Data Index: 318984 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5502. Min Range: -4.5502
Max Act: 4.4877. Min Act: -0.1700
Data Index: 6702167 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5502. Min Range: -4.5502
Max Act: 4.4565. Min Act: -0.1700
Data Index: 4602774 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5502. Min Range: -4.5502
Max Act: 4.4565. Min Act: -0.1700
Data Index: 8355307 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5502. Min Range: -4.5502
Max Act: 4.4252. Min Act: -0.1700
Data Index: 4199059 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5502. Min Range: -4.5502
Max Act: 4.3940. Min Act: -0.1700
Data Index: 6421322 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5502. Min Range: -4.5502
Max Act: 4.3940. Min Act: -0.1700
Data Index: 905268 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5502. Min Range: -4.5502
Max Act: 4.4252. Min Act: -0.1700
Data Index: 6251428 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5502. Min Range: -4.5502
Max Act: 4.3627. Min Act: -0.1700
Data Index: 7667641 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5502. Min Range: -4.5502
Max Act: 4.3627. Min Act: -0.1700
Data Index: 1335983 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5502. Min Range: -4.5502
Max Act: 4.3627. Min Act: -0.1700
Data Index: 2800925 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5502. Min Range: -4.5502
Max Act: 4.3627. Min Act: -0.1700
Data Index: 6214546 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5502. Min Range: -4.5502
Max Act: 4.3627. Min Act: -0.1700
Data Index: 140653 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5502. Min Range: -4.5502
Max Act: 4.3314. Min Act: -0.1700
Data Index: 5179195 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5502. Min Range: -4.5502
Max Act: 4.3627. Min Act: -0.1700
Data Index: 4689010 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5502. Min Range: -4.5502
Max Act: 4.3314. Min Act: -0.1700
Data Index: 323554 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5502. Min Range: -4.5502
Max Act: 4.3314. Min Act: -0.1700
Data Index: 6787982 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5502. Min Range: -4.5502
Max Act: 4.3002. Min Act: -0.1700
Data Index: 1350979 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #19