Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2580 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7153. Min Range: -4.7153
Max Act: 4.7153. Min Act: -0.1700
Data Index: 2991801 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7153. Min Range: -4.7153
Max Act: 4.6841. Min Act: -0.1700
Data Index: 8741964 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7153. Min Range: -4.7153
Max Act: 4.6528. Min Act: -0.1700
Data Index: 2065631 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7153. Min Range: -4.7153
Max Act: 4.6528. Min Act: -0.1700
Data Index: 6140413 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7153. Min Range: -4.7153
Max Act: 4.6216. Min Act: -0.1700
Data Index: 1194287 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7153. Min Range: -4.7153
Max Act: 4.6216. Min Act: -0.1700
Data Index: 8199387 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7153. Min Range: -4.7153
Max Act: 4.6216. Min Act: -0.1700
Data Index: 7655262 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7153. Min Range: -4.7153
Max Act: 4.6216. Min Act: -0.1700
Data Index: 1074269 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7153. Min Range: -4.7153
Max Act: 4.6216. Min Act: -0.1700
Data Index: 6563487 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7153. Min Range: -4.7153
Max Act: 4.6216. Min Act: -0.1700
Data Index: 1571111 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7153. Min Range: -4.7153
Max Act: 4.6216. Min Act: -0.1700
Data Index: 6124722 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7153. Min Range: -4.7153
Max Act: 4.6216. Min Act: -0.1700
Data Index: 5397064 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7153. Min Range: -4.7153
Max Act: 4.6216. Min Act: -0.1700
Data Index: 8710434 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7153. Min Range: -4.7153
Max Act: 4.6216. Min Act: -0.1700
Data Index: 4461629 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7153. Min Range: -4.7153
Max Act: 4.6216. Min Act: -0.1700
Data Index: 1503288 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7153. Min Range: -4.7153
Max Act: 4.5903. Min Act: -0.1700
Data Index: 2246372 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7153. Min Range: -4.7153
Max Act: 4.6216. Min Act: -0.1700
Data Index: 6801279 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7153. Min Range: -4.7153
Max Act: 4.5903. Min Act: -0.1700
Data Index: 7180927 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7153. Min Range: -4.7153
Max Act: 4.5903. Min Act: -0.1700
Data Index: 7283055 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7153. Min Range: -4.7153
Max Act: 4.5903. Min Act: -0.1700
Data Index: 3991583 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #19