Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2492 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.4040. Min Range: -8.4040
Max Act: 8.4040. Min Act: -0.1700
Data Index: 2097523 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4040. Min Range: -8.4040
Max Act: 8.4040. Min Act: -0.1700
Data Index: 4668787 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4040. Min Range: -8.4040
Max Act: 8.3415. Min Act: -0.1700
Data Index: 5039482 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4040. Min Range: -8.4040
Max Act: 8.2790. Min Act: -0.1700
Data Index: 6624184 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4040. Min Range: -8.4040
Max Act: 8.1853. Min Act: -0.1700
Data Index: 4186772 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4040. Min Range: -8.4040
Max Act: 8.1853. Min Act: -0.1700
Data Index: 3932045 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4040. Min Range: -8.4040
Max Act: 8.1853. Min Act: -0.1700
Data Index: 1256134 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4040. Min Range: -8.4040
Max Act: 8.1540. Min Act: -0.1700
Data Index: 6824394 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4040. Min Range: -8.4040
Max Act: 8.0915. Min Act: -0.1700
Data Index: 5104328 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4040. Min Range: -8.4040
Max Act: 8.0603. Min Act: -0.1700
Data Index: 7174679 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4040. Min Range: -8.4040
Max Act: 7.9978. Min Act: -0.1700
Data Index: 8516027 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4040. Min Range: -8.4040
Max Act: 8.0290. Min Act: -0.1700
Data Index: 3570784 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4040. Min Range: -8.4040
Max Act: 8.0290. Min Act: -0.1700
Data Index: 2180007 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4040. Min Range: -8.4040
Max Act: 7.9978. Min Act: -0.1700
Data Index: 6423022 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4040. Min Range: -8.4040
Max Act: 7.9665. Min Act: -0.1700
Data Index: 2893520 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4040. Min Range: -8.4040
Max Act: 7.9353. Min Act: -0.1700
Data Index: 1203028 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4040. Min Range: -8.4040
Max Act: 7.9040. Min Act: -0.1700
Data Index: 4911919 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4040. Min Range: -8.4040
Max Act: 7.9040. Min Act: -0.1700
Data Index: 8096337 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4040. Min Range: -8.4040
Max Act: 7.9040. Min Act: -0.1700
Data Index: 1317153 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4040. Min Range: -8.4040
Max Act: 7.8728. Min Act: -0.1700
Data Index: 1543948 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #19