Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4472 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8030. Min Range: -4.8030
Max Act: 4.8030. Min Act: -0.1700
Data Index: 2300276 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8030. Min Range: -4.8030
Max Act: 4.7717. Min Act: -0.1700
Data Index: 7463503 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8030. Min Range: -4.8030
Max Act: 4.7405. Min Act: -0.1700
Data Index: 2012878 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8030. Min Range: -4.8030
Max Act: 4.7092. Min Act: -0.1700
Data Index: 948099 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8030. Min Range: -4.8030
Max Act: 4.7092. Min Act: -0.1700
Data Index: 6301691 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8030. Min Range: -4.8030
Max Act: 4.6155. Min Act: -0.1700
Data Index: 6383681 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8030. Min Range: -4.8030
Max Act: 4.5530. Min Act: -0.1700
Data Index: 7229045 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8030. Min Range: -4.8030
Max Act: 4.5842. Min Act: -0.1700
Data Index: 4961395 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8030. Min Range: -4.8030
Max Act: 4.5530. Min Act: -0.1700
Data Index: 4955669 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8030. Min Range: -4.8030
Max Act: 4.5842. Min Act: -0.1700
Data Index: 5498929 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8030. Min Range: -4.8030
Max Act: 4.5530. Min Act: -0.1700
Data Index: 7267477 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8030. Min Range: -4.8030
Max Act: 4.5530. Min Act: -0.1700
Data Index: 7418888 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8030. Min Range: -4.8030
Max Act: 4.5217. Min Act: -0.1700
Data Index: 4029416 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8030. Min Range: -4.8030
Max Act: 4.4592. Min Act: -0.1700
Data Index: 5274973 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8030. Min Range: -4.8030
Max Act: 4.4905. Min Act: -0.1700
Data Index: 5579540 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8030. Min Range: -4.8030
Max Act: 4.4592. Min Act: -0.1700
Data Index: 7312247 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8030. Min Range: -4.8030
Max Act: 4.4592. Min Act: -0.1700
Data Index: 2142645 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8030. Min Range: -4.8030
Max Act: 4.4592. Min Act: -0.1700
Data Index: 55972 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8030. Min Range: -4.8030
Max Act: 4.4592. Min Act: -0.1700
Data Index: 3893803 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8030. Min Range: -4.8030
Max Act: 4.4280. Min Act: -0.1700
Data Index: 4681908 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #19