Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6390 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6421. Min Range: -7.6421
Max Act: 7.6421. Min Act: -0.1700
Data Index: 1133632 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6421. Min Range: -7.6421
Max Act: 7.6108. Min Act: -0.1700
Data Index: 2682058 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6421. Min Range: -7.6421
Max Act: 7.6421. Min Act: -0.1700
Data Index: 7985084 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6421. Min Range: -7.6421
Max Act: 7.5483. Min Act: -0.1700
Data Index: 6697141 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6421. Min Range: -7.6421
Max Act: 7.4858. Min Act: -0.1700
Data Index: 4143441 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6421. Min Range: -7.6421
Max Act: 7.4858. Min Act: -0.1700
Data Index: 6338129 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6421. Min Range: -7.6421
Max Act: 7.4233. Min Act: -0.1700
Data Index: 4868949 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6421. Min Range: -7.6421
Max Act: 7.4233. Min Act: -0.1700
Data Index: 4814792 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6421. Min Range: -7.6421
Max Act: 7.3296. Min Act: -0.1700
Data Index: 4746601 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6421. Min Range: -7.6421
Max Act: 7.3296. Min Act: -0.1700
Data Index: 2833672 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6421. Min Range: -7.6421
Max Act: 7.2671. Min Act: -0.1700
Data Index: 2074336 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6421. Min Range: -7.6421
Max Act: 7.2671. Min Act: -0.1700
Data Index: 5921988 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6421. Min Range: -7.6421
Max Act: 7.2358. Min Act: -0.1700
Data Index: 7398985 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6421. Min Range: -7.6421
Max Act: 7.2046. Min Act: -0.1700
Data Index: 8761585 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6421. Min Range: -7.6421
Max Act: 7.2046. Min Act: -0.1700
Data Index: 7499706 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6421. Min Range: -7.6421
Max Act: 7.1421. Min Act: -0.1700
Data Index: 8092244 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6421. Min Range: -7.6421
Max Act: 7.1421. Min Act: -0.1700
Data Index: 4983554 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6421. Min Range: -7.6421
Max Act: 7.1421. Min Act: -0.1700
Data Index: 594401 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6421. Min Range: -7.6421
Max Act: 7.1733. Min Act: -0.1700
Data Index: 2801427 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6421. Min Range: -7.6421
Max Act: 7.1108. Min Act: -0.1700
Data Index: 5318247 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #19