Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3220 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0461. Min Range: -4.0461
Max Act: 4.0461. Min Act: -0.1700
Data Index: 1515775 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0461. Min Range: -4.0461
Max Act: 3.9836. Min Act: -0.1700
Data Index: 2245503 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0461. Min Range: -4.0461
Max Act: 3.9836. Min Act: -0.1700
Data Index: 6533171 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0461. Min Range: -4.0461
Max Act: 3.8586. Min Act: -0.1700
Data Index: 8444940 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0461. Min Range: -4.0461
Max Act: 3.8429. Min Act: -0.1700
Data Index: 3699987 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0461. Min Range: -4.0461
Max Act: 3.8586. Min Act: -0.1700
Data Index: 6500739 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0461. Min Range: -4.0461
Max Act: 3.8273. Min Act: -0.1700
Data Index: 4533883 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0461. Min Range: -4.0461
Max Act: 3.8273. Min Act: -0.1700
Data Index: 7698381 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0461. Min Range: -4.0461
Max Act: 3.8117. Min Act: -0.1700
Data Index: 7862298 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0461. Min Range: -4.0461
Max Act: 3.7960. Min Act: -0.1700
Data Index: 4320084 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0461. Min Range: -4.0461
Max Act: 3.7960. Min Act: -0.1700
Data Index: 4335183 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0461. Min Range: -4.0461
Max Act: 3.7647. Min Act: -0.1700
Data Index: 5699967 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0461. Min Range: -4.0461
Max Act: 3.7647. Min Act: -0.1700
Data Index: 6572979 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0461. Min Range: -4.0461
Max Act: 3.7491. Min Act: -0.1700
Data Index: 4307082 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0461. Min Range: -4.0461
Max Act: 3.7491. Min Act: -0.1700
Data Index: 7715719 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0461. Min Range: -4.0461
Max Act: 3.7335. Min Act: -0.1700
Data Index: 6568255 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0461. Min Range: -4.0461
Max Act: 3.7178. Min Act: -0.1700
Data Index: 2260599 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0461. Min Range: -4.0461
Max Act: 3.6865. Min Act: -0.1700
Data Index: 8444939 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0461. Min Range: -4.0461
Max Act: 3.7178. Min Act: -0.1700
Data Index: 5085242 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0461. Min Range: -4.0461
Max Act: 3.7178. Min Act: -0.1700
Data Index: 509828 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #19