Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2640 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4222. Min Range: -5.4222
Max Act: 5.4222. Min Act: -0.1700
Data Index: 6821005 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4222. Min Range: -5.4222
Max Act: 5.2972. Min Act: -0.1700
Data Index: 6567677 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4222. Min Range: -5.4222
Max Act: 5.2035. Min Act: -0.1700
Data Index: 3905876 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4222. Min Range: -5.4222
Max Act: 5.2035. Min Act: -0.1700
Data Index: 8544471 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4222. Min Range: -5.4222
Max Act: 5.2035. Min Act: -0.1700
Data Index: 628619 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4222. Min Range: -5.4222
Max Act: 5.1410. Min Act: -0.1700
Data Index: 5873624 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4222. Min Range: -5.4222
Max Act: 5.1722. Min Act: -0.1700
Data Index: 2567542 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4222. Min Range: -5.4222
Max Act: 5.1410. Min Act: -0.1700
Data Index: 5873637 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4222. Min Range: -5.4222
Max Act: 5.1410. Min Act: -0.1700
Data Index: 2168826 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4222. Min Range: -5.4222
Max Act: 5.1410. Min Act: -0.1700
Data Index: 8194921 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4222. Min Range: -5.4222
Max Act: 5.1410. Min Act: -0.1700
Data Index: 1823863 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4222. Min Range: -5.4222
Max Act: 5.1097. Min Act: -0.1700
Data Index: 8399406 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4222. Min Range: -5.4222
Max Act: 5.0785. Min Act: -0.1700
Data Index: 1810463 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4222. Min Range: -5.4222
Max Act: 5.0785. Min Act: -0.1700
Data Index: 678320 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4222. Min Range: -5.4222
Max Act: 5.0785. Min Act: -0.1700
Data Index: 7559551 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4222. Min Range: -5.4222
Max Act: 5.0785. Min Act: -0.1700
Data Index: 3975834 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4222. Min Range: -5.4222
Max Act: 5.0160. Min Act: -0.1700
Data Index: 7791326 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4222. Min Range: -5.4222
Max Act: 5.0472. Min Act: -0.1700
Data Index: 7886766 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4222. Min Range: -5.4222
Max Act: 5.0472. Min Act: -0.1700
Data Index: 8092685 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4222. Min Range: -5.4222
Max Act: 5.0472. Min Act: -0.1700
Data Index: 2501370 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #19