Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 2558 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 7.5363. Min Range: -7.5363
Max Act: 7.5363. Min Act: -0.1700
Data Index: 4463454 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5363. Min Range: -7.5363
Max Act: 7.4113. Min Act: -0.1700
Data Index: 839540 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5363. Min Range: -7.5363
Max Act: 7.3488. Min Act: -0.1700
Data Index: 5824201 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5363. Min Range: -7.5363
Max Act: 7.1300. Min Act: -0.1700
Data Index: 8225942 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5363. Min Range: -7.5363
Max Act: 7.0363. Min Act: -0.1700
Data Index: 8357232 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5363. Min Range: -7.5363
Max Act: 6.9738. Min Act: -0.1700
Data Index: 839549 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5363. Min Range: -7.5363
Max Act: 7.0050. Min Act: -0.1700
Data Index: 7535639 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5363. Min Range: -7.5363
Max Act: 6.9425. Min Act: -0.1700
Data Index: 6225942 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5363. Min Range: -7.5363
Max Act: 6.9425. Min Act: -0.1700
Data Index: 7125310 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5363. Min Range: -7.5363
Max Act: 6.9113. Min Act: -0.1700
Data Index: 3425584 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5363. Min Range: -7.5363
Max Act: 6.9113. Min Act: -0.1700
Data Index: 956756 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5363. Min Range: -7.5363
Max Act: 6.9113. Min Act: -0.1700
Data Index: 7538235 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5363. Min Range: -7.5363
Max Act: 6.8800. Min Act: -0.1700
Data Index: 7691763 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5363. Min Range: -7.5363
Max Act: 6.8800. Min Act: -0.1700
Data Index: 6696238 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5363. Min Range: -7.5363
Max Act: 6.8800. Min Act: -0.1700
Data Index: 839531 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5363. Min Range: -7.5363
Max Act: 6.8800. Min Act: -0.1700
Data Index: 6215505 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5363. Min Range: -7.5363
Max Act: 6.8488. Min Act: -0.1700
Data Index: 6347695 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5363. Min Range: -7.5363
Max Act: 6.8488. Min Act: -0.1700
Data Index: 3747303 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5363. Min Range: -7.5363
Max Act: 6.8800. Min Act: -0.1700
Data Index: 839545 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5363. Min Range: -7.5363
Max Act: 6.7863. Min Act: -0.1700
Data Index: 4582675 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19