Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1572 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1140. Min Range: -4.1140
Max Act: 4.1140. Min Act: -0.1700
Data Index: 5369106 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1140. Min Range: -4.1140
Max Act: 3.9733. Min Act: -0.1700
Data Index: 4202664 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1140. Min Range: -4.1140
Max Act: 3.7232. Min Act: -0.1700
Data Index: 8808228 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1140. Min Range: -4.1140
Max Act: 3.6293. Min Act: -0.1700
Data Index: 7252756 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1140. Min Range: -4.1140
Max Act: 3.6293. Min Act: -0.1700
Data Index: 626170 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1140. Min Range: -4.1140
Max Act: 3.5823. Min Act: -0.1700
Data Index: 8558653 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1140. Min Range: -4.1140
Max Act: 3.5980. Min Act: -0.1700
Data Index: 4593844 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1140. Min Range: -4.1140
Max Act: 3.5667. Min Act: -0.1700
Data Index: 3596458 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1140. Min Range: -4.1140
Max Act: 3.5510. Min Act: -0.1700
Data Index: 3299448 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1140. Min Range: -4.1140
Max Act: 3.5667. Min Act: -0.1700
Data Index: 850824 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1140. Min Range: -4.1140
Max Act: 3.5354. Min Act: -0.1700
Data Index: 7798880 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1140. Min Range: -4.1140
Max Act: 3.5354. Min Act: -0.1700
Data Index: 731695 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1140. Min Range: -4.1140
Max Act: 3.5197. Min Act: -0.1700
Data Index: 614610 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1140. Min Range: -4.1140
Max Act: 3.5197. Min Act: -0.1700
Data Index: 1027781 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1140. Min Range: -4.1140
Max Act: 3.5197. Min Act: -0.1700
Data Index: 4134528 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1140. Min Range: -4.1140
Max Act: 3.4884. Min Act: -0.1700
Data Index: 6884599 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1140. Min Range: -4.1140
Max Act: 3.4727. Min Act: -0.1700
Data Index: 3692046 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1140. Min Range: -4.1140
Max Act: 3.4884. Min Act: -0.1700
Data Index: 3362686 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1140. Min Range: -4.1140
Max Act: 3.4727. Min Act: -0.1700
Data Index: 3448752 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1140. Min Range: -4.1140
Max Act: 3.4571. Min Act: -0.1700
Data Index: 4861374 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #19