Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 364 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.3931. Min Range: -7.3931
Max Act: 7.3931. Min Act: -0.1700
Data Index: 7610386 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3931. Min Range: -7.3931
Max Act: 7.2369. Min Act: -0.1700
Data Index: 5806820 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3931. Min Range: -7.3931
Max Act: 7.1431. Min Act: -0.1700
Data Index: 7985438 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3931. Min Range: -7.3931
Max Act: 7.1431. Min Act: -0.1700
Data Index: 766740 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3931. Min Range: -7.3931
Max Act: 7.1119. Min Act: -0.1700
Data Index: 7833671 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3931. Min Range: -7.3931
Max Act: 6.9556. Min Act: -0.1700
Data Index: 7240074 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3931. Min Range: -7.3931
Max Act: 7.0181. Min Act: -0.1700
Data Index: 5637715 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3931. Min Range: -7.3931
Max Act: 7.0181. Min Act: -0.1700
Data Index: 3416720 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3931. Min Range: -7.3931
Max Act: 7.0181. Min Act: -0.1700
Data Index: 1023994 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3931. Min Range: -7.3931
Max Act: 7.0494. Min Act: -0.1700
Data Index: 6995874 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3931. Min Range: -7.3931
Max Act: 6.9244. Min Act: -0.1700
Data Index: 7152665 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3931. Min Range: -7.3931
Max Act: 6.9556. Min Act: -0.1700
Data Index: 1805524 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3931. Min Range: -7.3931
Max Act: 6.9244. Min Act: -0.1700
Data Index: 1755812 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3931. Min Range: -7.3931
Max Act: 6.9244. Min Act: -0.1700
Data Index: 800172 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3931. Min Range: -7.3931
Max Act: 6.9556. Min Act: -0.1700
Data Index: 2625002 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3931. Min Range: -7.3931
Max Act: 6.8619. Min Act: -0.1700
Data Index: 7129441 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3931. Min Range: -7.3931
Max Act: 6.8619. Min Act: -0.1700
Data Index: 3542358 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3931. Min Range: -7.3931
Max Act: 6.8306. Min Act: -0.1700
Data Index: 692942 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3931. Min Range: -7.3931
Max Act: 6.7681. Min Act: -0.1700
Data Index: 2123807 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3931. Min Range: -7.3931
Max Act: 6.7681. Min Act: -0.1700
Data Index: 7358971 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #19