Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 12 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9735. Min Range: -4.9735
Max Act: 4.9735. Min Act: -0.1700
Data Index: 7502755 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9735. Min Range: -4.9735
Max Act: 4.5985. Min Act: -0.1700
Data Index: 3483135 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9735. Min Range: -4.9735
Max Act: 4.5985. Min Act: -0.1700
Data Index: 2364543 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9735. Min Range: -4.9735
Max Act: 4.5360. Min Act: -0.1700
Data Index: 567725 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9735. Min Range: -4.9735
Max Act: 4.4110. Min Act: -0.1700
Data Index: 297437 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9735. Min Range: -4.9735
Max Act: 4.3797. Min Act: -0.1700
Data Index: 1188665 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9735. Min Range: -4.9735
Max Act: 4.3797. Min Act: -0.1700
Data Index: 552810 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9735. Min Range: -4.9735
Max Act: 4.3485. Min Act: -0.1700
Data Index: 7027105 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9735. Min Range: -4.9735
Max Act: 4.3172. Min Act: -0.1700
Data Index: 7330458 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9735. Min Range: -4.9735
Max Act: 4.3485. Min Act: -0.1700
Data Index: 8004813 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9735. Min Range: -4.9735
Max Act: 4.2860. Min Act: -0.1700
Data Index: 4717140 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9735. Min Range: -4.9735
Max Act: 4.2547. Min Act: -0.1700
Data Index: 601024 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9735. Min Range: -4.9735
Max Act: 4.2547. Min Act: -0.1700
Data Index: 6039343 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9735. Min Range: -4.9735
Max Act: 4.2547. Min Act: -0.1700
Data Index: 297221 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9735. Min Range: -4.9735
Max Act: 4.2235. Min Act: -0.1700
Data Index: 4616963 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9735. Min Range: -4.9735
Max Act: 4.1922. Min Act: -0.1700
Data Index: 3302852 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9735. Min Range: -4.9735
Max Act: 4.2235. Min Act: -0.1700
Data Index: 7792942 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9735. Min Range: -4.9735
Max Act: 4.1922. Min Act: -0.1700
Data Index: 1739823 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9735. Min Range: -4.9735
Max Act: 4.1922. Min Act: -0.1700
Data Index: 3761587 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9735. Min Range: -4.9735
Max Act: 4.1922. Min Act: -0.1700
Data Index: 1566657 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #19