Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1659 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.1072. Min Range: -2.1072
Max Act: 2.1072. Min Act: -0.1700
Data Index: 5419100 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1072. Min Range: -2.1072
Max Act: 2.0569. Min Act: -0.1700
Data Index: 549669 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1072. Min Range: -2.1072
Max Act: 2.0063. Min Act: -0.1700
Data Index: 401494 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1072. Min Range: -2.1072
Max Act: 1.9725. Min Act: -0.1700
Data Index: 7474662 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1072. Min Range: -2.1072
Max Act: 1.9555. Min Act: -0.1700
Data Index: 3279588 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1072. Min Range: -2.1072
Max Act: 1.9555. Min Act: -0.1700
Data Index: 5107793 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1072. Min Range: -2.1072
Max Act: 1.9385. Min Act: -0.1700
Data Index: 7003615 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1072. Min Range: -2.1072
Max Act: 1.9385. Min Act: -0.1700
Data Index: 1431352 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1072. Min Range: -2.1072
Max Act: 1.9555. Min Act: -0.1700
Data Index: 4430435 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1072. Min Range: -2.1072
Max Act: 1.9385. Min Act: -0.1700
Data Index: 1836408 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1072. Min Range: -2.1072
Max Act: 1.9215. Min Act: -0.1700
Data Index: 5903074 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1072. Min Range: -2.1072
Max Act: 1.9215. Min Act: -0.1700
Data Index: 4142531 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1072. Min Range: -2.1072
Max Act: 1.9215. Min Act: -0.1700
Data Index: 6533407 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1072. Min Range: -2.1072
Max Act: 1.9385. Min Act: -0.1700
Data Index: 7358510 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1072. Min Range: -2.1072
Max Act: 1.9385. Min Act: -0.1700
Data Index: 4945580 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1072. Min Range: -2.1072
Max Act: 1.9385. Min Act: -0.1700
Data Index: 1487423 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1072. Min Range: -2.1072
Max Act: 1.9215. Min Act: -0.1700
Data Index: 8135331 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1072. Min Range: -2.1072
Max Act: 1.9385. Min Act: -0.1700
Data Index: 4889890 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1072. Min Range: -2.1072
Max Act: 1.9045. Min Act: -0.1700
Data Index: 209547 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1072. Min Range: -2.1072
Max Act: 1.9045. Min Act: -0.1700
Data Index: 5899202 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #19