Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5108 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9973. Min Range: -2.9973
Max Act: 2.9973. Min Act: -0.1700
Data Index: 5941702 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9973. Min Range: -2.9973
Max Act: 2.7273. Min Act: -0.1692
Data Index: 283097 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9973. Min Range: -2.9973
Max Act: 2.7433. Min Act: -0.1700
Data Index: 7202379 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9973. Min Range: -2.9973
Max Act: 2.7113. Min Act: -0.1700
Data Index: 2219923 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9973. Min Range: -2.9973
Max Act: 2.7113. Min Act: -0.1700
Data Index: 5111887 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9973. Min Range: -2.9973
Max Act: 2.7113. Min Act: -0.1678
Data Index: 8428475 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9973. Min Range: -2.9973
Max Act: 2.6953. Min Act: -0.1700
Data Index: 8493115 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9973. Min Range: -2.9973
Max Act: 2.6953. Min Act: -0.1632
Data Index: 3013199 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9973. Min Range: -2.9973
Max Act: 2.6953. Min Act: -0.1700
Data Index: 8786257 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9973. Min Range: -2.9973
Max Act: 2.6953. Min Act: -0.1700
Data Index: 1490698 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9973. Min Range: -2.9973
Max Act: 2.6953. Min Act: -0.1700
Data Index: 6493661 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9973. Min Range: -2.9973
Max Act: 2.6953. Min Act: -0.1700
Data Index: 835272 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9973. Min Range: -2.9973
Max Act: 2.6953. Min Act: -0.1700
Data Index: 2251604 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9973. Min Range: -2.9973
Max Act: 2.6953. Min Act: -0.1700
Data Index: 2555711 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9973. Min Range: -2.9973
Max Act: 2.6953. Min Act: -0.1700
Data Index: 1066550 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9973. Min Range: -2.9973
Max Act: 2.6953. Min Act: -0.1700
Data Index: 2337357 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9973. Min Range: -2.9973
Max Act: 2.6953. Min Act: -0.1700
Data Index: 2763371 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9973. Min Range: -2.9973
Max Act: 2.6953. Min Act: -0.1700
Data Index: 5035023 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9973. Min Range: -2.9973
Max Act: 2.6953. Min Act: -0.1700
Data Index: 4066118 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9973. Min Range: -2.9973
Max Act: 2.6793. Min Act: -0.1700
Data Index: 2676465 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19