Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 43 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8653. Min Range: -1.8653
Max Act: 1.8653. Min Act: -0.1700
Data Index: 6331581 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8653. Min Range: -1.8653
Max Act: 1.8053. Min Act: -0.1700
Data Index: 7864242 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8653. Min Range: -1.8653
Max Act: 1.8053. Min Act: -0.1700
Data Index: 3795463 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8653. Min Range: -1.8653
Max Act: 1.7795. Min Act: -0.1700
Data Index: 3503889 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8653. Min Range: -1.8653
Max Act: 1.7881. Min Act: -0.1700
Data Index: 8045633 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8653. Min Range: -1.8653
Max Act: 1.7622. Min Act: -0.1700
Data Index: 7036323 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8653. Min Range: -1.8653
Max Act: 1.7536. Min Act: -0.1700
Data Index: 7963548 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8653. Min Range: -1.8653
Max Act: 1.7536. Min Act: -0.1700
Data Index: 7481728 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8653. Min Range: -1.8653
Max Act: 1.7277. Min Act: -0.1698
Data Index: 1963322 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8653. Min Range: -1.8653
Max Act: 1.7536. Min Act: -0.1700
Data Index: 6799016 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8653. Min Range: -1.8653
Max Act: 1.7363. Min Act: -0.1700
Data Index: 1500022 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8653. Min Range: -1.8653
Max Act: 1.7363. Min Act: -0.1700
Data Index: 6331582 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8653. Min Range: -1.8653
Max Act: 1.7363. Min Act: -0.1700
Data Index: 4510370 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8653. Min Range: -1.8653
Max Act: 1.7277. Min Act: -0.1700
Data Index: 8531147 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8653. Min Range: -1.8653
Max Act: 1.7277. Min Act: -0.1700
Data Index: 3341300 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8653. Min Range: -1.8653
Max Act: 1.7277. Min Act: -0.1700
Data Index: 1379100 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8653. Min Range: -1.8653
Max Act: 1.7190. Min Act: -0.1700
Data Index: 3676163 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8653. Min Range: -1.8653
Max Act: 1.7190. Min Act: -0.1700
Data Index: 3530420 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8653. Min Range: -1.8653
Max Act: 1.7190. Min Act: -0.1700
Data Index: 1384676 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8653. Min Range: -1.8653
Max Act: 1.7103. Min Act: -0.1699
Data Index: 427219 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #19