Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3488 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7952. Min Range: -6.7952
Max Act: 6.7952. Min Act: -0.1700
Data Index: 776025 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7952. Min Range: -6.7952
Max Act: 6.7015. Min Act: -0.1700
Data Index: 1620678 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7952. Min Range: -6.7952
Max Act: 6.6702. Min Act: -0.1700
Data Index: 3258224 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7952. Min Range: -6.7952
Max Act: 6.7015. Min Act: -0.1700
Data Index: 7469835 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7952. Min Range: -6.7952
Max Act: 6.7015. Min Act: -0.1700
Data Index: 7097078 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7952. Min Range: -6.7952
Max Act: 6.6702. Min Act: -0.1700
Data Index: 764521 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7952. Min Range: -6.7952
Max Act: 6.6702. Min Act: -0.1700
Data Index: 1832158 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7952. Min Range: -6.7952
Max Act: 6.6702. Min Act: -0.1700
Data Index: 3139767 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7952. Min Range: -6.7952
Max Act: 6.6077. Min Act: -0.1700
Data Index: 6337538 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7952. Min Range: -6.7952
Max Act: 6.6077. Min Act: -0.1700
Data Index: 8653347 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7952. Min Range: -6.7952
Max Act: 6.5765. Min Act: -0.1700
Data Index: 4723861 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7952. Min Range: -6.7952
Max Act: 6.5765. Min Act: -0.1700
Data Index: 1806130 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7952. Min Range: -6.7952
Max Act: 6.5765. Min Act: -0.1700
Data Index: 2492607 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7952. Min Range: -6.7952
Max Act: 6.5765. Min Act: -0.1700
Data Index: 7873736 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7952. Min Range: -6.7952
Max Act: 6.5765. Min Act: -0.1700
Data Index: 2105965 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7952. Min Range: -6.7952
Max Act: 6.5765. Min Act: -0.1700
Data Index: 6674427 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7952. Min Range: -6.7952
Max Act: 6.5452. Min Act: -0.1700
Data Index: 6871967 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7952. Min Range: -6.7952
Max Act: 6.5140. Min Act: -0.1700
Data Index: 7186603 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7952. Min Range: -6.7952
Max Act: 6.5140. Min Act: -0.1700
Data Index: 5946167 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7952. Min Range: -6.7952
Max Act: 6.5452. Min Act: -0.1700
Data Index: 85613 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #19