Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 25 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.5565. Min Range: -8.5565
Max Act: 8.5565. Min Act: -0.1700
Data Index: 2089658 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5565. Min Range: -8.5565
Max Act: 7.9940. Min Act: -0.1700
Data Index: 5430935 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5565. Min Range: -8.5565
Max Act: 7.8690. Min Act: -0.1700
Data Index: 4788509 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5565. Min Range: -8.5565
Max Act: 7.7127. Min Act: -0.1700
Data Index: 1628474 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5565. Min Range: -8.5565
Max Act: 7.6502. Min Act: -0.1700
Data Index: 8321519 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5565. Min Range: -8.5565
Max Act: 7.5252. Min Act: -0.1700
Data Index: 6647448 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5565. Min Range: -8.5565
Max Act: 7.4940. Min Act: -0.1700
Data Index: 4955921 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5565. Min Range: -8.5565
Max Act: 7.4940. Min Act: -0.1700
Data Index: 5581843 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5565. Min Range: -8.5565
Max Act: 7.3065. Min Act: -0.1700
Data Index: 7774781 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5565. Min Range: -8.5565
Max Act: 7.2752. Min Act: -0.1700
Data Index: 7910754 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5565. Min Range: -8.5565
Max Act: 7.2752. Min Act: -0.1700
Data Index: 6647450 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5565. Min Range: -8.5565
Max Act: 7.2440. Min Act: -0.1700
Data Index: 5769768 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5565. Min Range: -8.5565
Max Act: 7.2127. Min Act: -0.1700
Data Index: 5626086 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5565. Min Range: -8.5565
Max Act: 7.2440. Min Act: -0.1700
Data Index: 4040985 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5565. Min Range: -8.5565
Max Act: 7.1815. Min Act: -0.1700
Data Index: 8805089 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5565. Min Range: -8.5565
Max Act: 7.1815. Min Act: -0.1700
Data Index: 1367369 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5565. Min Range: -8.5565
Max Act: 7.1815. Min Act: -0.1700
Data Index: 7981155 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5565. Min Range: -8.5565
Max Act: 7.1502. Min Act: -0.1700
Data Index: 1927242 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5565. Min Range: -8.5565
Max Act: 7.0565. Min Act: -0.1700
Data Index: 5372109 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5565. Min Range: -8.5565
Max Act: 7.0565. Min Act: -0.1700
Data Index: 8805090 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #19