Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2675 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.5503. Min Range: -7.5503
Max Act: 7.5503. Min Act: -0.1700
Data Index: 2129523 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5503. Min Range: -7.5503
Max Act: 7.4878. Min Act: -0.1700
Data Index: 6621346 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5503. Min Range: -7.5503
Max Act: 7.4566. Min Act: -0.1700
Data Index: 5934345 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5503. Min Range: -7.5503
Max Act: 7.3628. Min Act: -0.1700
Data Index: 3231688 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5503. Min Range: -7.5503
Max Act: 7.3628. Min Act: -0.1700
Data Index: 4888252 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5503. Min Range: -7.5503
Max Act: 7.3316. Min Act: -0.1700
Data Index: 7372763 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5503. Min Range: -7.5503
Max Act: 7.2691. Min Act: -0.1700
Data Index: 3064594 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5503. Min Range: -7.5503
Max Act: 7.2378. Min Act: -0.1700
Data Index: 7211890 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5503. Min Range: -7.5503
Max Act: 7.2378. Min Act: -0.1700
Data Index: 5132291 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5503. Min Range: -7.5503
Max Act: 7.2066. Min Act: -0.1700
Data Index: 8318370 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5503. Min Range: -7.5503
Max Act: 7.2066. Min Act: -0.1700
Data Index: 2835551 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5503. Min Range: -7.5503
Max Act: 7.2066. Min Act: -0.1700
Data Index: 2221620 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5503. Min Range: -7.5503
Max Act: 7.2066. Min Act: -0.1700
Data Index: 4881598 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5503. Min Range: -7.5503
Max Act: 7.2066. Min Act: -0.1700
Data Index: 7440808 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5503. Min Range: -7.5503
Max Act: 7.1753. Min Act: -0.1700
Data Index: 2456963 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5503. Min Range: -7.5503
Max Act: 7.1753. Min Act: -0.1700
Data Index: 1223251 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5503. Min Range: -7.5503
Max Act: 7.1753. Min Act: -0.1700
Data Index: 4666669 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5503. Min Range: -7.5503
Max Act: 7.1441. Min Act: -0.1700
Data Index: 7986797 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5503. Min Range: -7.5503
Max Act: 7.1441. Min Act: -0.1700
Data Index: 2940679 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5503. Min Range: -7.5503
Max Act: 7.1128. Min Act: -0.1700
Data Index: 626088 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #19