Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3564 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8210. Min Range: -4.8210
Max Act: 4.8210. Min Act: -0.1700
Data Index: 6513634 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8210. Min Range: -4.8210
Max Act: 4.8210. Min Act: -0.1700
Data Index: 5123934 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8210. Min Range: -4.8210
Max Act: 4.7897. Min Act: -0.1700
Data Index: 1280525 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8210. Min Range: -4.8210
Max Act: 4.7897. Min Act: -0.1700
Data Index: 5645874 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8210. Min Range: -4.8210
Max Act: 4.6647. Min Act: -0.1700
Data Index: 4705197 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8210. Min Range: -4.8210
Max Act: 4.6335. Min Act: -0.1700
Data Index: 5700987 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8210. Min Range: -4.8210
Max Act: 4.6647. Min Act: -0.1700
Data Index: 2562016 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8210. Min Range: -4.8210
Max Act: 4.6335. Min Act: -0.1700
Data Index: 1292558 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8210. Min Range: -4.8210
Max Act: 4.6335. Min Act: -0.1700
Data Index: 194832 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8210. Min Range: -4.8210
Max Act: 4.6022. Min Act: -0.1700
Data Index: 1988232 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8210. Min Range: -4.8210
Max Act: 4.5710. Min Act: -0.1700
Data Index: 4422094 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8210. Min Range: -4.8210
Max Act: 4.5710. Min Act: -0.1700
Data Index: 5562471 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8210. Min Range: -4.8210
Max Act: 4.5710. Min Act: -0.1700
Data Index: 76211 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8210. Min Range: -4.8210
Max Act: 4.6022. Min Act: -0.1700
Data Index: 6691959 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8210. Min Range: -4.8210
Max Act: 4.6022. Min Act: -0.1700
Data Index: 569060 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8210. Min Range: -4.8210
Max Act: 4.5710. Min Act: -0.1700
Data Index: 4813425 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8210. Min Range: -4.8210
Max Act: 4.5397. Min Act: -0.1700
Data Index: 6691961 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8210. Min Range: -4.8210
Max Act: 4.6335. Min Act: -0.1700
Data Index: 4331799 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8210. Min Range: -4.8210
Max Act: 4.6022. Min Act: -0.1700
Data Index: 320140 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8210. Min Range: -4.8210
Max Act: 4.6022. Min Act: -0.1700
Data Index: 6802901 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #19