Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2820 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9042. Min Range: -7.9042
Max Act: 7.9042. Min Act: -0.1700
Data Index: 4702025 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9042. Min Range: -7.9042
Max Act: 7.9042. Min Act: -0.1700
Data Index: 4464963 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9042. Min Range: -7.9042
Max Act: 7.9042. Min Act: -0.1700
Data Index: 8809112 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9042. Min Range: -7.9042
Max Act: 7.9042. Min Act: -0.1700
Data Index: 8702740 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9042. Min Range: -7.9042
Max Act: 7.9042. Min Act: -0.1700
Data Index: 3852795 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9042. Min Range: -7.9042
Max Act: 7.9042. Min Act: -0.1700
Data Index: 3852792 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9042. Min Range: -7.9042
Max Act: 7.9042. Min Act: -0.1700
Data Index: 8135819 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9042. Min Range: -7.9042
Max Act: 7.9042. Min Act: -0.1700
Data Index: 7607493 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9042. Min Range: -7.9042
Max Act: 7.9042. Min Act: -0.1700
Data Index: 7392731 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9042. Min Range: -7.9042
Max Act: 7.9042. Min Act: -0.1700
Data Index: 747529 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9042. Min Range: -7.9042
Max Act: 7.9042. Min Act: -0.1700
Data Index: 747534 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9042. Min Range: -7.9042
Max Act: 7.9042. Min Act: -0.1700
Data Index: 7392735 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9042. Min Range: -7.9042
Max Act: 7.9042. Min Act: -0.1700
Data Index: 6860956 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9042. Min Range: -7.9042
Max Act: 7.9042. Min Act: -0.1700
Data Index: 969014 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9042. Min Range: -7.9042
Max Act: 7.9042. Min Act: -0.1700
Data Index: 5798902 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9042. Min Range: -7.9042
Max Act: 7.9042. Min Act: -0.1700
Data Index: 3250332 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9042. Min Range: -7.9042
Max Act: 7.8417. Min Act: -0.1700
Data Index: 4037089 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9042. Min Range: -7.9042
Max Act: 7.8417. Min Act: -0.1700
Data Index: 1856724 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9042. Min Range: -7.9042
Max Act: 7.8417. Min Act: -0.1700
Data Index: 4671886 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9042. Min Range: -7.9042
Max Act: 7.8417. Min Act: -0.1700
Data Index: 2073339 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #19