Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2196 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6979. Min Range: -7.6979
Max Act: 7.6979. Min Act: -0.1700
Data Index: 4497240 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6979. Min Range: -7.6979
Max Act: 7.3854. Min Act: -0.1700
Data Index: 8527608 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6979. Min Range: -7.6979
Max Act: 7.1979. Min Act: -0.1700
Data Index: 74319 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6979. Min Range: -7.6979
Max Act: 7.1041. Min Act: -0.1700
Data Index: 8341673 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6979. Min Range: -7.6979
Max Act: 7.1041. Min Act: -0.1700
Data Index: 6454144 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6979. Min Range: -7.6979
Max Act: 7.0104. Min Act: -0.1700
Data Index: 7927230 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6979. Min Range: -7.6979
Max Act: 7.0104. Min Act: -0.1700
Data Index: 4779922 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6979. Min Range: -7.6979
Max Act: 6.9791. Min Act: -0.1700
Data Index: 2519955 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6979. Min Range: -7.6979
Max Act: 6.9791. Min Act: -0.1700
Data Index: 6337651 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6979. Min Range: -7.6979
Max Act: 6.9479. Min Act: -0.1700
Data Index: 8525637 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6979. Min Range: -7.6979
Max Act: 6.9479. Min Act: -0.1700
Data Index: 1836878 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6979. Min Range: -7.6979
Max Act: 6.9166. Min Act: -0.1700
Data Index: 6433396 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6979. Min Range: -7.6979
Max Act: 6.8854. Min Act: -0.1700
Data Index: 7502024 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6979. Min Range: -7.6979
Max Act: 6.8854. Min Act: -0.1700
Data Index: 2629498 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6979. Min Range: -7.6979
Max Act: 6.9166. Min Act: -0.1700
Data Index: 8112208 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6979. Min Range: -7.6979
Max Act: 6.8854. Min Act: -0.1700
Data Index: 36924 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6979. Min Range: -7.6979
Max Act: 6.8229. Min Act: -0.1700
Data Index: 2908586 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6979. Min Range: -7.6979
Max Act: 6.8541. Min Act: -0.1700
Data Index: 3897203 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6979. Min Range: -7.6979
Max Act: 6.8541. Min Act: -0.1700
Data Index: 5773582 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6979. Min Range: -7.6979
Max Act: 6.8229. Min Act: -0.1700
Data Index: 4594570 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #19