Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3338 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.4879. Min Range: -2.4879
Max Act: 2.4879. Min Act: -0.1700
Data Index: 7628955 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4879. Min Range: -2.4879
Max Act: 2.4392. Min Act: -0.1700
Data Index: 7370715 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4879. Min Range: -2.4879
Max Act: 2.4229. Min Act: -0.1700
Data Index: 4797392 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4879. Min Range: -2.4879
Max Act: 2.4066. Min Act: -0.1700
Data Index: 1819568 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4879. Min Range: -2.4879
Max Act: 2.4066. Min Act: -0.1700
Data Index: 6595138 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4879. Min Range: -2.4879
Max Act: 2.4066. Min Act: -0.1700
Data Index: 6705987 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4879. Min Range: -2.4879
Max Act: 2.4066. Min Act: -0.1700
Data Index: 8194992 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4879. Min Range: -2.4879
Max Act: 2.4229. Min Act: -0.1700
Data Index: 966418 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4879. Min Range: -2.4879
Max Act: 2.3739. Min Act: -0.1700
Data Index: 6324094 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4879. Min Range: -2.4879
Max Act: 2.3903. Min Act: -0.1700
Data Index: 2996187 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4879. Min Range: -2.4879
Max Act: 2.3903. Min Act: -0.1700
Data Index: 1468847 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4879. Min Range: -2.4879
Max Act: 2.3739. Min Act: -0.1700
Data Index: 6829138 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4879. Min Range: -2.4879
Max Act: 2.3739. Min Act: -0.1700
Data Index: 985968 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4879. Min Range: -2.4879
Max Act: 2.3739. Min Act: -0.1700
Data Index: 202169 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4879. Min Range: -2.4879
Max Act: 2.3576. Min Act: -0.1700
Data Index: 387289 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4879. Min Range: -2.4879
Max Act: 2.3739. Min Act: -0.1700
Data Index: 2055963 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4879. Min Range: -2.4879
Max Act: 2.3739. Min Act: -0.1700
Data Index: 4420545 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4879. Min Range: -2.4879
Max Act: 2.3576. Min Act: -0.1700
Data Index: 5952322 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4879. Min Range: -2.4879
Max Act: 2.3412. Min Act: -0.1700
Data Index: 5763109 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4879. Min Range: -2.4879
Max Act: 2.3576. Min Act: -0.1700
Data Index: 365899 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #19