Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2611 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5596. Min Range: -5.5596
Max Act: 5.5596. Min Act: -0.1700
Data Index: 727573 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5596. Min Range: -5.5596
Max Act: 5.2783. Min Act: -0.1700
Data Index: 6807985 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5596. Min Range: -5.5596
Max Act: 5.1533. Min Act: -0.1700
Data Index: 1051190 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5596. Min Range: -5.5596
Max Act: 5.0283. Min Act: -0.1700
Data Index: 3498622 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5596. Min Range: -5.5596
Max Act: 4.9658. Min Act: -0.1700
Data Index: 1694742 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5596. Min Range: -5.5596
Max Act: 4.9033. Min Act: -0.1700
Data Index: 5523593 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5596. Min Range: -5.5596
Max Act: 4.9033. Min Act: -0.1700
Data Index: 4925973 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5596. Min Range: -5.5596
Max Act: 4.9033. Min Act: -0.1700
Data Index: 4671037 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5596. Min Range: -5.5596
Max Act: 4.9033. Min Act: -0.1700
Data Index: 6373440 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5596. Min Range: -5.5596
Max Act: 4.8721. Min Act: -0.1700
Data Index: 3893976 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5596. Min Range: -5.5596
Max Act: 4.8721. Min Act: -0.1700
Data Index: 3776280 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5596. Min Range: -5.5596
Max Act: 4.8096. Min Act: -0.1700
Data Index: 80470 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5596. Min Range: -5.5596
Max Act: 4.8721. Min Act: -0.1700
Data Index: 4942839 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5596. Min Range: -5.5596
Max Act: 4.8721. Min Act: -0.1700
Data Index: 2793708 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5596. Min Range: -5.5596
Max Act: 4.8096. Min Act: -0.1700
Data Index: 5627976 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5596. Min Range: -5.5596
Max Act: 4.8096. Min Act: -0.1700
Data Index: 1756034 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5596. Min Range: -5.5596
Max Act: 4.7783. Min Act: -0.1700
Data Index: 1916410 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5596. Min Range: -5.5596
Max Act: 4.7158. Min Act: -0.1700
Data Index: 5198594 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5596. Min Range: -5.5596
Max Act: 4.7471. Min Act: -0.1700
Data Index: 3779753 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5596. Min Range: -5.5596
Max Act: 4.7158. Min Act: -0.1700
Data Index: 6195959 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #19