Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 204 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1084. Min Range: -5.1084
Max Act: 5.1084. Min Act: -0.1700
Data Index: 5657037 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1084. Min Range: -5.1084
Max Act: 5.0459. Min Act: -0.1700
Data Index: 1106983 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1084. Min Range: -5.1084
Max Act: 5.0459. Min Act: -0.1700
Data Index: 4848474 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1084. Min Range: -5.1084
Max Act: 5.0771. Min Act: -0.1700
Data Index: 7748685 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1084. Min Range: -5.1084
Max Act: 4.9834. Min Act: -0.1700
Data Index: 3695901 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1084. Min Range: -5.1084
Max Act: 4.9834. Min Act: -0.1700
Data Index: 5966902 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1084. Min Range: -5.1084
Max Act: 4.9521. Min Act: -0.1700
Data Index: 4848475 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1084. Min Range: -5.1084
Max Act: 4.9209. Min Act: -0.1700
Data Index: 2410071 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1084. Min Range: -5.1084
Max Act: 4.9521. Min Act: -0.1700
Data Index: 492530 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1084. Min Range: -5.1084
Max Act: 4.9209. Min Act: -0.1700
Data Index: 6981143 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1084. Min Range: -5.1084
Max Act: 4.9209. Min Act: -0.1700
Data Index: 5290018 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1084. Min Range: -5.1084
Max Act: 4.8896. Min Act: -0.1700
Data Index: 1331002 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1084. Min Range: -5.1084
Max Act: 4.8896. Min Act: -0.1700
Data Index: 8070630 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1084. Min Range: -5.1084
Max Act: 4.8271. Min Act: -0.1700
Data Index: 6874582 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1084. Min Range: -5.1084
Max Act: 4.8271. Min Act: -0.1700
Data Index: 5966907 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1084. Min Range: -5.1084
Max Act: 4.7959. Min Act: -0.1700
Data Index: 3570864 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1084. Min Range: -5.1084
Max Act: 4.8584. Min Act: -0.1700
Data Index: 7358959 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1084. Min Range: -5.1084
Max Act: 4.7646. Min Act: -0.1700
Data Index: 2945826 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1084. Min Range: -5.1084
Max Act: 4.7646. Min Act: -0.1700
Data Index: 2597065 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1084. Min Range: -5.1084
Max Act: 4.7334. Min Act: -0.1700
Data Index: 2311187 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #19