Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3264 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3005. Min Range: -3.3005
Max Act: 3.3005. Min Act: -0.1700
Data Index: 4367495 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3005. Min Range: -3.3005
Max Act: 3.2691. Min Act: -0.1700
Data Index: 6541889 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3005. Min Range: -3.3005
Max Act: 3.2691. Min Act: -0.1700
Data Index: 5560068 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3005. Min Range: -3.3005
Max Act: 3.2691. Min Act: -0.1700
Data Index: 3357625 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3005. Min Range: -3.3005
Max Act: 3.2219. Min Act: -0.1700
Data Index: 2479291 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3005. Min Range: -3.3005
Max Act: 3.2062. Min Act: -0.1700
Data Index: 5269193 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3005. Min Range: -3.3005
Max Act: 3.2219. Min Act: -0.1700
Data Index: 4437376 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3005. Min Range: -3.3005
Max Act: 3.1433. Min Act: -0.1700
Data Index: 7120969 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3005. Min Range: -3.3005
Max Act: 3.1590. Min Act: -0.1700
Data Index: 1570398 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3005. Min Range: -3.3005
Max Act: 3.1433. Min Act: -0.1700
Data Index: 6479930 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3005. Min Range: -3.3005
Max Act: 3.1275. Min Act: -0.1700
Data Index: 1434374 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3005. Min Range: -3.3005
Max Act: 3.0960. Min Act: -0.1700
Data Index: 7977154 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3005. Min Range: -3.3005
Max Act: 3.0960. Min Act: -0.1700
Data Index: 274608 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3005. Min Range: -3.3005
Max Act: 3.0960. Min Act: -0.1700
Data Index: 1274533 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3005. Min Range: -3.3005
Max Act: 3.0960. Min Act: -0.1700
Data Index: 3668452 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3005. Min Range: -3.3005
Max Act: 3.0803. Min Act: -0.1700
Data Index: 3739783 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3005. Min Range: -3.3005
Max Act: 3.0803. Min Act: -0.1700
Data Index: 3407591 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3005. Min Range: -3.3005
Max Act: 3.0645. Min Act: -0.1700
Data Index: 6627011 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3005. Min Range: -3.3005
Max Act: 3.0487. Min Act: -0.1700
Data Index: 2433959 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3005. Min Range: -3.3005
Max Act: 3.0645. Min Act: -0.1700
Data Index: 6610726 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19