Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2648 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5478. Min Range: -5.5478
Max Act: 5.5478. Min Act: -0.1700
Data Index: 6663641 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5478. Min Range: -5.5478
Max Act: 5.4853. Min Act: -0.1700
Data Index: 8037073 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5478. Min Range: -5.5478
Max Act: 5.3290. Min Act: -0.1700
Data Index: 5135901 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5478. Min Range: -5.5478
Max Act: 5.4228. Min Act: -0.1700
Data Index: 3079379 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5478. Min Range: -5.5478
Max Act: 5.3290. Min Act: -0.1700
Data Index: 5914495 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5478. Min Range: -5.5478
Max Act: 5.3290. Min Act: -0.1700
Data Index: 6949982 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5478. Min Range: -5.5478
Max Act: 5.2978. Min Act: -0.1700
Data Index: 6351115 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5478. Min Range: -5.5478
Max Act: 5.2665. Min Act: -0.1700
Data Index: 6006167 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5478. Min Range: -5.5478
Max Act: 5.2040. Min Act: -0.1700
Data Index: 560316 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5478. Min Range: -5.5478
Max Act: 5.2040. Min Act: -0.1700
Data Index: 3829354 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5478. Min Range: -5.5478
Max Act: 5.2040. Min Act: -0.1700
Data Index: 3611210 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5478. Min Range: -5.5478
Max Act: 5.2353. Min Act: -0.1700
Data Index: 6614185 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5478. Min Range: -5.5478
Max Act: 5.2040. Min Act: -0.1700
Data Index: 4046771 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5478. Min Range: -5.5478
Max Act: 5.1728. Min Act: -0.1700
Data Index: 1109669 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5478. Min Range: -5.5478
Max Act: 5.2040. Min Act: -0.1700
Data Index: 4886339 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5478. Min Range: -5.5478
Max Act: 5.2353. Min Act: -0.1700
Data Index: 7287967 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5478. Min Range: -5.5478
Max Act: 5.2040. Min Act: -0.1700
Data Index: 5495704 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5478. Min Range: -5.5478
Max Act: 5.1728. Min Act: -0.1700
Data Index: 7296349 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5478. Min Range: -5.5478
Max Act: 5.2040. Min Act: -0.1700
Data Index: 4915974 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5478. Min Range: -5.5478
Max Act: 5.1415. Min Act: -0.1700
Data Index: 6767939 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #19