Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1130 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6985. Min Range: -6.6985
Max Act: 6.6985. Min Act: -0.1700
Data Index: 7955253 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6985. Min Range: -6.6985
Max Act: 6.5110. Min Act: -0.1700
Data Index: 6572116 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6985. Min Range: -6.6985
Max Act: 6.2923. Min Act: -0.1700
Data Index: 5124875 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6985. Min Range: -6.6985
Max Act: 6.2923. Min Act: -0.1700
Data Index: 6992606 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6985. Min Range: -6.6985
Max Act: 6.2923. Min Act: -0.1700
Data Index: 2908414 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6985. Min Range: -6.6985
Max Act: 6.2610. Min Act: -0.1700
Data Index: 2136922 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6985. Min Range: -6.6985
Max Act: 6.2610. Min Act: -0.1700
Data Index: 4344850 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6985. Min Range: -6.6985
Max Act: 6.2298. Min Act: -0.1700
Data Index: 5153235 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6985. Min Range: -6.6985
Max Act: 6.2298. Min Act: -0.1700
Data Index: 528772 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6985. Min Range: -6.6985
Max Act: 6.1048. Min Act: -0.1700
Data Index: 7597310 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6985. Min Range: -6.6985
Max Act: 6.1360. Min Act: -0.1700
Data Index: 8774339 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6985. Min Range: -6.6985
Max Act: 6.1360. Min Act: -0.1700
Data Index: 2146322 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6985. Min Range: -6.6985
Max Act: 6.1360. Min Act: -0.1700
Data Index: 7597766 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6985. Min Range: -6.6985
Max Act: 6.1360. Min Act: -0.1700
Data Index: 4468795 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6985. Min Range: -6.6985
Max Act: 6.1360. Min Act: -0.1700
Data Index: 2556334 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6985. Min Range: -6.6985
Max Act: 6.1048. Min Act: -0.1700
Data Index: 6500582 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6985. Min Range: -6.6985
Max Act: 6.1048. Min Act: -0.1700
Data Index: 1714548 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6985. Min Range: -6.6985
Max Act: 6.1048. Min Act: -0.1700
Data Index: 8408060 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6985. Min Range: -6.6985
Max Act: 6.1360. Min Act: -0.1700
Data Index: 2689439 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6985. Min Range: -6.6985
Max Act: 6.1048. Min Act: -0.1700
Data Index: 277020 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #19