Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3454 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8349. Min Range: -5.8349
Max Act: 5.8349. Min Act: -0.1700
Data Index: 2788350 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8349. Min Range: -5.8349
Max Act: 5.7724. Min Act: -0.1700
Data Index: 5944790 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8349. Min Range: -5.8349
Max Act: 5.7724. Min Act: -0.1700
Data Index: 3193652 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8349. Min Range: -5.8349
Max Act: 5.7099. Min Act: -0.1700
Data Index: 1082231 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8349. Min Range: -5.8349
Max Act: 5.7099. Min Act: -0.1700
Data Index: 2610721 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8349. Min Range: -5.8349
Max Act: 5.6786. Min Act: -0.1700
Data Index: 1723178 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8349. Min Range: -5.8349
Max Act: 5.6786. Min Act: -0.1700
Data Index: 1062691 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8349. Min Range: -5.8349
Max Act: 5.6786. Min Act: -0.1700
Data Index: 264628 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8349. Min Range: -5.8349
Max Act: 5.6786. Min Act: -0.1700
Data Index: 5481522 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8349. Min Range: -5.8349
Max Act: 5.6786. Min Act: -0.1700
Data Index: 7042869 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8349. Min Range: -5.8349
Max Act: 5.6786. Min Act: -0.1700
Data Index: 916968 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8349. Min Range: -5.8349
Max Act: 5.6786. Min Act: -0.1700
Data Index: 1076224 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8349. Min Range: -5.8349
Max Act: 5.6786. Min Act: -0.1700
Data Index: 281641 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8349. Min Range: -5.8349
Max Act: 5.6786. Min Act: -0.1700
Data Index: 2197987 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8349. Min Range: -5.8349
Max Act: 5.6786. Min Act: -0.1700
Data Index: 1304775 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8349. Min Range: -5.8349
Max Act: 5.6786. Min Act: -0.1700
Data Index: 5992833 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8349. Min Range: -5.8349
Max Act: 5.6474. Min Act: -0.1700
Data Index: 3553449 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8349. Min Range: -5.8349
Max Act: 5.6161. Min Act: -0.1700
Data Index: 3796469 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8349. Min Range: -5.8349
Max Act: 5.6161. Min Act: -0.1700
Data Index: 7160235 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8349. Min Range: -5.8349
Max Act: 5.6161. Min Act: -0.1700
Data Index: 5547087 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19