Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3172 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.7389. Min Range: -1.7389
Max Act: 1.7389. Min Act: -0.1700
Data Index: 7692372 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7389. Min Range: -1.7389
Max Act: 1.6956. Min Act: -0.1700
Data Index: 7799252 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7389. Min Range: -1.7389
Max Act: 1.6695. Min Act: -0.1700
Data Index: 6656269 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7389. Min Range: -1.7389
Max Act: 1.6521. Min Act: -0.1700
Data Index: 3580612 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7389. Min Range: -1.7389
Max Act: 1.6434. Min Act: -0.1694
Data Index: 7332200 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7389. Min Range: -1.7389
Max Act: 1.6086. Min Act: -0.1699
Data Index: 1388665 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7389. Min Range: -1.7389
Max Act: 1.6086. Min Act: -0.1698
Data Index: 5948910 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7389. Min Range: -1.7389
Max Act: 1.6086. Min Act: -0.1694
Data Index: 788272 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7389. Min Range: -1.7389
Max Act: 1.5911. Min Act: -0.1700
Data Index: 4428428 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7389. Min Range: -1.7389
Max Act: 1.5911. Min Act: -0.1700
Data Index: 5932985 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7389. Min Range: -1.7389
Max Act: 1.5998. Min Act: -0.1700
Data Index: 2739602 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7389. Min Range: -1.7389
Max Act: 1.5998. Min Act: -0.1700
Data Index: 4128403 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7389. Min Range: -1.7389
Max Act: 1.5824. Min Act: -0.1697
Data Index: 3998712 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7389. Min Range: -1.7389
Max Act: 1.5911. Min Act: -0.1700
Data Index: 2333338 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7389. Min Range: -1.7389
Max Act: 1.5911. Min Act: -0.1695
Data Index: 2320150 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7389. Min Range: -1.7389
Max Act: 1.5824. Min Act: -0.1700
Data Index: 3286648 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7389. Min Range: -1.7389
Max Act: 1.5736. Min Act: -0.1700
Data Index: 5630371 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7389. Min Range: -1.7389
Max Act: 1.5824. Min Act: -0.1700
Data Index: 6166533 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7389. Min Range: -1.7389
Max Act: 1.5736. Min Act: -0.1699
Data Index: 394294 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7389. Min Range: -1.7389
Max Act: 1.5824. Min Act: -0.1700
Data Index: 2100207 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19