Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4901 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0244. Min Range: -9.0244
Max Act: 9.0244. Min Act: -0.1700
Data Index: 6231988 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0244. Min Range: -9.0244
Max Act: 9.0244. Min Act: -0.1700
Data Index: 6041813 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0244. Min Range: -9.0244
Max Act: 8.9619. Min Act: -0.1700
Data Index: 8752327 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0244. Min Range: -9.0244
Max Act: 9.0244. Min Act: -0.1700
Data Index: 1050050 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0244. Min Range: -9.0244
Max Act: 8.9619. Min Act: -0.1700
Data Index: 7860026 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0244. Min Range: -9.0244
Max Act: 8.8994. Min Act: -0.1700
Data Index: 4732705 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0244. Min Range: -9.0244
Max Act: 8.7119. Min Act: -0.1700
Data Index: 29758 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0244. Min Range: -9.0244
Max Act: 8.6494. Min Act: -0.1700
Data Index: 1957736 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0244. Min Range: -9.0244
Max Act: 8.6494. Min Act: -0.1700
Data Index: 6286160 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0244. Min Range: -9.0244
Max Act: 8.7119. Min Act: -0.1700
Data Index: 3816523 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0244. Min Range: -9.0244
Max Act: 8.6494. Min Act: -0.1699
Data Index: 1634660 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0244. Min Range: -9.0244
Max Act: 8.6494. Min Act: -0.1700
Data Index: 6876302 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0244. Min Range: -9.0244
Max Act: 8.5869. Min Act: -0.1700
Data Index: 7885661 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0244. Min Range: -9.0244
Max Act: 8.5869. Min Act: -0.1700
Data Index: 6923390 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0244. Min Range: -9.0244
Max Act: 8.5869. Min Act: -0.1700
Data Index: 3846211 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0244. Min Range: -9.0244
Max Act: 8.5869. Min Act: -0.1700
Data Index: 6786684 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0244. Min Range: -9.0244
Max Act: 8.5869. Min Act: -0.1700
Data Index: 5434291 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0244. Min Range: -9.0244
Max Act: 8.5869. Min Act: -0.1700
Data Index: 158195 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0244. Min Range: -9.0244
Max Act: 8.5869. Min Act: -0.1700
Data Index: 1972247 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0244. Min Range: -9.0244
Max Act: 8.5244. Min Act: -0.1700
Data Index: 8726220 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #19