Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 6 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.2067. Min Range: -2.2067
Max Act: 2.2067. Min Act: -0.1700
Data Index: 4446377 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2067. Min Range: -2.2067
Max Act: 2.1901. Min Act: -0.1700
Data Index: 6885703 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2067. Min Range: -2.2067
Max Act: 2.1901. Min Act: -0.1700
Data Index: 7371571 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2067. Min Range: -2.2067
Max Act: 2.1735. Min Act: -0.1700
Data Index: 2312625 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2067. Min Range: -2.2067
Max Act: 2.1569. Min Act: -0.1700
Data Index: 3082129 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2067. Min Range: -2.2067
Max Act: 2.1402. Min Act: -0.1700
Data Index: 7408208 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2067. Min Range: -2.2067
Max Act: 2.1235. Min Act: -0.1700
Data Index: 2645740 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2067. Min Range: -2.2067
Max Act: 2.1235. Min Act: -0.1700
Data Index: 8805637 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2067. Min Range: -2.2067
Max Act: 2.0900. Min Act: -0.1700
Data Index: 1852964 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2067. Min Range: -2.2067
Max Act: 2.0733. Min Act: -0.1700
Data Index: 6129308 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2067. Min Range: -2.2067
Max Act: 2.0900. Min Act: -0.1700
Data Index: 6774513 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2067. Min Range: -2.2067
Max Act: 2.0733. Min Act: -0.1700
Data Index: 7333813 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2067. Min Range: -2.2067
Max Act: 2.0900. Min Act: -0.1700
Data Index: 1891952 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2067. Min Range: -2.2067
Max Act: 2.0733. Min Act: -0.1700
Data Index: 2935174 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2067. Min Range: -2.2067
Max Act: 2.0733. Min Act: -0.1700
Data Index: 5119570 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2067. Min Range: -2.2067
Max Act: 2.0733. Min Act: -0.1700
Data Index: 1280836 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2067. Min Range: -2.2067
Max Act: 2.0733. Min Act: -0.1700
Data Index: 2588180 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2067. Min Range: -2.2067
Max Act: 2.0396. Min Act: -0.1700
Data Index: 6298257 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2067. Min Range: -2.2067
Max Act: 2.0565. Min Act: -0.1700
Data Index: 7345479 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2067. Min Range: -2.2067
Max Act: 2.0565. Min Act: -0.1700
Data Index: 1317201 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19