Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2408 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5829. Min Range: -3.5829
Max Act: 3.5516. Min Act: -0.1700
Data Index: 4147535 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5829. Min Range: -3.5829
Max Act: 3.5829. Min Act: -0.1700
Data Index: 4243959 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5829. Min Range: -3.5829
Max Act: 3.5046. Min Act: -0.1700
Data Index: 2922615 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5829. Min Range: -3.5829
Max Act: 3.4576. Min Act: -0.1700
Data Index: 31761 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5829. Min Range: -3.5829
Max Act: 3.4420. Min Act: -0.1700
Data Index: 1905678 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5829. Min Range: -3.5829
Max Act: 3.4420. Min Act: -0.1700
Data Index: 6304214 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5829. Min Range: -3.5829
Max Act: 3.4420. Min Act: -0.1700
Data Index: 6405753 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5829. Min Range: -3.5829
Max Act: 3.4420. Min Act: -0.1700
Data Index: 2375312 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5829. Min Range: -3.5829
Max Act: 3.4420. Min Act: -0.1700
Data Index: 6790604 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5829. Min Range: -3.5829
Max Act: 3.4420. Min Act: -0.1700
Data Index: 4496674 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5829. Min Range: -3.5829
Max Act: 3.4263. Min Act: -0.1700
Data Index: 5666074 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5829. Min Range: -3.5829
Max Act: 3.4263. Min Act: -0.1700
Data Index: 993852 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5829. Min Range: -3.5829
Max Act: 3.3949. Min Act: -0.1700
Data Index: 7368971 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5829. Min Range: -3.5829
Max Act: 3.3792. Min Act: -0.1700
Data Index: 1211786 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5829. Min Range: -3.5829
Max Act: 3.3949. Min Act: -0.1700
Data Index: 3663243 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5829. Min Range: -3.5829
Max Act: 3.3792. Min Act: -0.1700
Data Index: 1489075 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5829. Min Range: -3.5829
Max Act: 3.3636. Min Act: -0.1700
Data Index: 3378469 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5829. Min Range: -3.5829
Max Act: 3.3636. Min Act: -0.1700
Data Index: 6590759 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5829. Min Range: -3.5829
Max Act: 3.3322. Min Act: -0.1700
Data Index: 6340703 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5829. Min Range: -3.5829
Max Act: 3.3636. Min Act: -0.1700
Data Index: 1184216 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #19