Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1545 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5679. Min Range: -4.5679
Max Act: 4.5679. Min Act: -0.1700
Data Index: 5509378 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5679. Min Range: -4.5679
Max Act: 4.5054. Min Act: -0.1700
Data Index: 1481623 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5679. Min Range: -4.5679
Max Act: 4.4741. Min Act: -0.1700
Data Index: 2700287 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5679. Min Range: -4.5679
Max Act: 4.4741. Min Act: -0.1700
Data Index: 3896965 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5679. Min Range: -4.5679
Max Act: 4.4429. Min Act: -0.1700
Data Index: 8027107 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5679. Min Range: -4.5679
Max Act: 4.4429. Min Act: -0.1700
Data Index: 3537065 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5679. Min Range: -4.5679
Max Act: 4.4116. Min Act: -0.1700
Data Index: 6506156 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5679. Min Range: -4.5679
Max Act: 4.4429. Min Act: -0.1700
Data Index: 5679657 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5679. Min Range: -4.5679
Max Act: 4.4116. Min Act: -0.1700
Data Index: 7395121 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5679. Min Range: -4.5679
Max Act: 4.4116. Min Act: -0.1699
Data Index: 7862456 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5679. Min Range: -4.5679
Max Act: 4.4116. Min Act: -0.1700
Data Index: 822663 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5679. Min Range: -4.5679
Max Act: 4.4429. Min Act: -0.1700
Data Index: 1863360 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5679. Min Range: -4.5679
Max Act: 4.4116. Min Act: -0.1700
Data Index: 5406483 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5679. Min Range: -4.5679
Max Act: 4.4116. Min Act: -0.1700
Data Index: 5028491 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5679. Min Range: -4.5679
Max Act: 4.4116. Min Act: -0.1700
Data Index: 4302691 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5679. Min Range: -4.5679
Max Act: 4.4116. Min Act: -0.1700
Data Index: 281925 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5679. Min Range: -4.5679
Max Act: 4.4116. Min Act: -0.1700
Data Index: 1253863 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5679. Min Range: -4.5679
Max Act: 4.3804. Min Act: -0.1700
Data Index: 5939134 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5679. Min Range: -4.5679
Max Act: 4.4116. Min Act: -0.1700
Data Index: 4959520 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5679. Min Range: -4.5679
Max Act: 4.3804. Min Act: -0.1700
Data Index: 7369964 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19