Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5479 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6428. Min Range: -6.6428
Max Act: 6.6428. Min Act: -0.1700
Data Index: 4557460 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6428. Min Range: -6.6428
Max Act: 6.6116. Min Act: -0.1700
Data Index: 5886467 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6428. Min Range: -6.6428
Max Act: 6.5803. Min Act: -0.1700
Data Index: 8309620 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6428. Min Range: -6.6428
Max Act: 6.4553. Min Act: -0.1700
Data Index: 3427375 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6428. Min Range: -6.6428
Max Act: 6.3616. Min Act: -0.1700
Data Index: 1228740 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6428. Min Range: -6.6428
Max Act: 6.3303. Min Act: -0.1700
Data Index: 1826827 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6428. Min Range: -6.6428
Max Act: 6.3616. Min Act: -0.1700
Data Index: 4226034 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6428. Min Range: -6.6428
Max Act: 6.3616. Min Act: -0.1700
Data Index: 1368408 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6428. Min Range: -6.6428
Max Act: 6.3616. Min Act: -0.1700
Data Index: 8609145 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6428. Min Range: -6.6428
Max Act: 6.2678. Min Act: -0.1700
Data Index: 447970 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6428. Min Range: -6.6428
Max Act: 6.2366. Min Act: -0.1700
Data Index: 1484565 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6428. Min Range: -6.6428
Max Act: 6.2366. Min Act: -0.1700
Data Index: 4921224 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6428. Min Range: -6.6428
Max Act: 6.2053. Min Act: -0.1700
Data Index: 2016799 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6428. Min Range: -6.6428
Max Act: 6.2053. Min Act: -0.1700
Data Index: 1435813 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6428. Min Range: -6.6428
Max Act: 6.2053. Min Act: -0.1700
Data Index: 7160429 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6428. Min Range: -6.6428
Max Act: 6.1428. Min Act: -0.1700
Data Index: 8787934 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6428. Min Range: -6.6428
Max Act: 6.1428. Min Act: -0.1700
Data Index: 7136898 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6428. Min Range: -6.6428
Max Act: 6.1116. Min Act: -0.1700
Data Index: 1503143 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6428. Min Range: -6.6428
Max Act: 6.1116. Min Act: -0.1700
Data Index: 3147996 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6428. Min Range: -6.6428
Max Act: 6.0803. Min Act: -0.1700
Data Index: 5346216 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #19