Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1677 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.2051. Min Range: -2.2051
Max Act: 2.2051. Min Act: -0.1700
Data Index: 6335688 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2051. Min Range: -2.2051
Max Act: 2.1885. Min Act: -0.1700
Data Index: 1648999 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2051. Min Range: -2.2051
Max Act: 2.1219. Min Act: -0.1700
Data Index: 921782 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2051. Min Range: -2.2051
Max Act: 2.0884. Min Act: -0.1700
Data Index: 2840551 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2051. Min Range: -2.2051
Max Act: 2.0548. Min Act: -0.1700
Data Index: 8438802 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2051. Min Range: -2.2051
Max Act: 2.0043. Min Act: -0.1700
Data Index: 8706397 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2051. Min Range: -2.2051
Max Act: 2.0211. Min Act: -0.1700
Data Index: 5996268 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2051. Min Range: -2.2051
Max Act: 2.0211. Min Act: -0.1700
Data Index: 510212 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2051. Min Range: -2.2051
Max Act: 1.9874. Min Act: -0.1700
Data Index: 3930450 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2051. Min Range: -2.2051
Max Act: 1.9874. Min Act: -0.1700
Data Index: 7708398 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2051. Min Range: -2.2051
Max Act: 2.0043. Min Act: -0.1700
Data Index: 7025405 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2051. Min Range: -2.2051
Max Act: 1.9874. Min Act: -0.1700
Data Index: 2034967 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2051. Min Range: -2.2051
Max Act: 1.9874. Min Act: -0.1700
Data Index: 5549311 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2051. Min Range: -2.2051
Max Act: 1.9874. Min Act: -0.1700
Data Index: 5425357 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2051. Min Range: -2.2051
Max Act: 1.9874. Min Act: -0.1700
Data Index: 5133040 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2051. Min Range: -2.2051
Max Act: 1.9704. Min Act: -0.1700
Data Index: 6258135 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2051. Min Range: -2.2051
Max Act: 1.9704. Min Act: -0.1700
Data Index: 5319707 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2051. Min Range: -2.2051
Max Act: 1.9704. Min Act: -0.1700
Data Index: 5260313 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2051. Min Range: -2.2051
Max Act: 1.9874. Min Act: -0.1700
Data Index: 4493327 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2051. Min Range: -2.2051
Max Act: 1.9704. Min Act: -0.1700
Data Index: 7874575 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #19