Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 436 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1725. Min Range: -4.1725
Max Act: 4.1725. Min Act: -0.1700
Data Index: 3222654 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1725. Min Range: -4.1725
Max Act: 3.9537. Min Act: -0.1700
Data Index: 1411550 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1725. Min Range: -4.1725
Max Act: 3.9537. Min Act: -0.1700
Data Index: 8108063 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1725. Min Range: -4.1725
Max Act: 3.9224. Min Act: -0.1700
Data Index: 5653723 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1725. Min Range: -4.1725
Max Act: 3.8599. Min Act: -0.1700
Data Index: 8108064 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1725. Min Range: -4.1725
Max Act: 3.8599. Min Act: -0.1700
Data Index: 1045540 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1725. Min Range: -4.1725
Max Act: 3.8286. Min Act: -0.1700
Data Index: 2500755 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1725. Min Range: -4.1725
Max Act: 3.7973. Min Act: -0.1700
Data Index: 7256982 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1725. Min Range: -4.1725
Max Act: 3.8599. Min Act: -0.1700
Data Index: 4990426 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1725. Min Range: -4.1725
Max Act: 3.7973. Min Act: -0.1700
Data Index: 2682624 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1725. Min Range: -4.1725
Max Act: 3.7973. Min Act: -0.1700
Data Index: 2646808 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1725. Min Range: -4.1725
Max Act: 3.7348. Min Act: -0.1700
Data Index: 6805689 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1725. Min Range: -4.1725
Max Act: 3.7661. Min Act: -0.1700
Data Index: 7241104 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1725. Min Range: -4.1725
Max Act: 3.7661. Min Act: -0.1700
Data Index: 6083258 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1725. Min Range: -4.1725
Max Act: 3.7348. Min Act: -0.1700
Data Index: 6732452 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1725. Min Range: -4.1725
Max Act: 3.7348. Min Act: -0.1700
Data Index: 53571 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1725. Min Range: -4.1725
Max Act: 3.7035. Min Act: -0.1700
Data Index: 3847881 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1725. Min Range: -4.1725
Max Act: 3.7348. Min Act: -0.1700
Data Index: 1044076 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1725. Min Range: -4.1725
Max Act: 3.7035. Min Act: -0.1700
Data Index: 5349316 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1725. Min Range: -4.1725
Max Act: 3.7348. Min Act: -0.1700
Data Index: 7873384 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #19