Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 40 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2320. Min Range: -4.2320
Max Act: 4.2320. Min Act: -0.1700
Data Index: 1212048 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2320. Min Range: -4.2320
Max Act: 4.1383. Min Act: -0.1700
Data Index: 5226638 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2320. Min Range: -4.2320
Max Act: 4.1070. Min Act: -0.1700
Data Index: 7389154 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2320. Min Range: -4.2320
Max Act: 4.0758. Min Act: -0.1700
Data Index: 5385100 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2320. Min Range: -4.2320
Max Act: 4.0758. Min Act: -0.1700
Data Index: 200697 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2320. Min Range: -4.2320
Max Act: 4.0758. Min Act: -0.1700
Data Index: 372513 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2320. Min Range: -4.2320
Max Act: 4.0445. Min Act: -0.1700
Data Index: 6460642 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2320. Min Range: -4.2320
Max Act: 4.1070. Min Act: -0.1700
Data Index: 1012084 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2320. Min Range: -4.2320
Max Act: 4.0758. Min Act: -0.1700
Data Index: 177597 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2320. Min Range: -4.2320
Max Act: 4.0758. Min Act: -0.1700
Data Index: 7654318 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2320. Min Range: -4.2320
Max Act: 4.0445. Min Act: -0.1700
Data Index: 6627559 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2320. Min Range: -4.2320
Max Act: 4.0758. Min Act: -0.1700
Data Index: 1360177 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2320. Min Range: -4.2320
Max Act: 4.0445. Min Act: -0.1700
Data Index: 1476214 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2320. Min Range: -4.2320
Max Act: 4.0132. Min Act: -0.1700
Data Index: 2648035 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2320. Min Range: -4.2320
Max Act: 4.0132. Min Act: -0.1700
Data Index: 2763802 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2320. Min Range: -4.2320
Max Act: 3.9820. Min Act: -0.1700
Data Index: 6034426 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2320. Min Range: -4.2320
Max Act: 4.0132. Min Act: -0.1700
Data Index: 5725697 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2320. Min Range: -4.2320
Max Act: 4.0132. Min Act: -0.1700
Data Index: 4428670 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2320. Min Range: -4.2320
Max Act: 4.0132. Min Act: -0.1700
Data Index: 8287064 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2320. Min Range: -4.2320
Max Act: 3.9820. Min Act: -0.1700
Data Index: 6799934 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #19