Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3764 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5917. Min Range: -3.5917
Max Act: 3.5917. Min Act: -0.1700
Data Index: 1449432 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5917. Min Range: -3.5917
Max Act: 3.5604. Min Act: -0.1700
Data Index: 4683108 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5917. Min Range: -3.5917
Max Act: 3.5291. Min Act: -0.1700
Data Index: 3717844 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5917. Min Range: -3.5917
Max Act: 3.5291. Min Act: -0.1700
Data Index: 8275722 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5917. Min Range: -3.5917
Max Act: 3.5291. Min Act: -0.1700
Data Index: 8084836 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5917. Min Range: -3.5917
Max Act: 3.5291. Min Act: -0.1700
Data Index: 6702043 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5917. Min Range: -3.5917
Max Act: 3.4978. Min Act: -0.1700
Data Index: 8032852 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5917. Min Range: -3.5917
Max Act: 3.4978. Min Act: -0.1700
Data Index: 6332861 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5917. Min Range: -3.5917
Max Act: 3.4978. Min Act: -0.1700
Data Index: 8196146 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5917. Min Range: -3.5917
Max Act: 3.4978. Min Act: -0.1700
Data Index: 67189 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5917. Min Range: -3.5917
Max Act: 3.4978. Min Act: -0.1700
Data Index: 6040379 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5917. Min Range: -3.5917
Max Act: 3.4978. Min Act: -0.1700
Data Index: 8413221 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5917. Min Range: -3.5917
Max Act: 3.5291. Min Act: -0.1700
Data Index: 6059234 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5917. Min Range: -3.5917
Max Act: 3.4664. Min Act: -0.1700
Data Index: 4076552 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5917. Min Range: -3.5917
Max Act: 3.4664. Min Act: -0.1700
Data Index: 4816230 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5917. Min Range: -3.5917
Max Act: 3.4664. Min Act: -0.1700
Data Index: 200085 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5917. Min Range: -3.5917
Max Act: 3.4664. Min Act: -0.1700
Data Index: 5305266 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5917. Min Range: -3.5917
Max Act: 3.4664. Min Act: -0.1700
Data Index: 220363 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5917. Min Range: -3.5917
Max Act: 3.4664. Min Act: -0.1700
Data Index: 5529226 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5917. Min Range: -3.5917
Max Act: 3.4664. Min Act: -0.1700
Data Index: 5568911 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19