Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 406 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.2342. Min Range: -7.2342
Max Act: 7.2342. Min Act: -0.1700
Data Index: 3980312 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2342. Min Range: -7.2342
Max Act: 7.2342. Min Act: -0.1700
Data Index: 5699475 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2342. Min Range: -7.2342
Max Act: 7.2342. Min Act: -0.1700
Data Index: 616006 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2342. Min Range: -7.2342
Max Act: 7.2342. Min Act: -0.1700
Data Index: 4771818 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2342. Min Range: -7.2342
Max Act: 7.1717. Min Act: -0.1700
Data Index: 2932755 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2342. Min Range: -7.2342
Max Act: 7.1717. Min Act: -0.1700
Data Index: 7284829 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2342. Min Range: -7.2342
Max Act: 7.1717. Min Act: -0.1700
Data Index: 5335010 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2342. Min Range: -7.2342
Max Act: 7.1092. Min Act: -0.1700
Data Index: 7803261 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2342. Min Range: -7.2342
Max Act: 7.1092. Min Act: -0.1700
Data Index: 8804124 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2342. Min Range: -7.2342
Max Act: 7.1092. Min Act: -0.1700
Data Index: 8790088 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2342. Min Range: -7.2342
Max Act: 7.1092. Min Act: -0.1700
Data Index: 8135253 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2342. Min Range: -7.2342
Max Act: 7.1092. Min Act: -0.1700
Data Index: 8003777 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2342. Min Range: -7.2342
Max Act: 7.1092. Min Act: -0.1700
Data Index: 1218514 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2342. Min Range: -7.2342
Max Act: 7.1092. Min Act: -0.1700
Data Index: 7757452 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2342. Min Range: -7.2342
Max Act: 7.1092. Min Act: -0.1700
Data Index: 7155030 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2342. Min Range: -7.2342
Max Act: 7.1092. Min Act: -0.1700
Data Index: 5938571 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2342. Min Range: -7.2342
Max Act: 7.1092. Min Act: -0.1700
Data Index: 5842570 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2342. Min Range: -7.2342
Max Act: 7.0467. Min Act: -0.1700
Data Index: 3249494 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2342. Min Range: -7.2342
Max Act: 7.0467. Min Act: -0.1700
Data Index: 3426093 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2342. Min Range: -7.2342
Max Act: 7.0467. Min Act: -0.1700
Data Index: 5697015 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19