Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2269 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3930. Min Range: -7.3930
Max Act: 7.3930. Min Act: -0.1700
Data Index: 2277322 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3930. Min Range: -7.3930
Max Act: 7.2055. Min Act: -0.1700
Data Index: 953266 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3930. Min Range: -7.3930
Max Act: 6.7368. Min Act: -0.1700
Data Index: 3836873 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3930. Min Range: -7.3930
Max Act: 6.6430. Min Act: -0.1700
Data Index: 1156722 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3930. Min Range: -7.3930
Max Act: 6.5805. Min Act: -0.1700
Data Index: 7917884 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3930. Min Range: -7.3930
Max Act: 6.5493. Min Act: -0.1700
Data Index: 1183155 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3930. Min Range: -7.3930
Max Act: 6.5493. Min Act: -0.1700
Data Index: 3516867 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3930. Min Range: -7.3930
Max Act: 6.5493. Min Act: -0.1700
Data Index: 5310364 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3930. Min Range: -7.3930
Max Act: 6.3618. Min Act: -0.1700
Data Index: 6065635 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3930. Min Range: -7.3930
Max Act: 6.3618. Min Act: -0.1700
Data Index: 4271830 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3930. Min Range: -7.3930
Max Act: 6.3305. Min Act: -0.1700
Data Index: 6073690 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3930. Min Range: -7.3930
Max Act: 6.2993. Min Act: -0.1700
Data Index: 4609957 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3930. Min Range: -7.3930
Max Act: 6.2680. Min Act: -0.1700
Data Index: 6094936 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3930. Min Range: -7.3930
Max Act: 6.2368. Min Act: -0.1700
Data Index: 8331035 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3930. Min Range: -7.3930
Max Act: 6.2368. Min Act: -0.1700
Data Index: 5996313 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3930. Min Range: -7.3930
Max Act: 6.2680. Min Act: -0.1700
Data Index: 1919665 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3930. Min Range: -7.3930
Max Act: 6.2368. Min Act: -0.1700
Data Index: 7974867 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3930. Min Range: -7.3930
Max Act: 6.1430. Min Act: -0.1700
Data Index: 3687567 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3930. Min Range: -7.3930
Max Act: 6.1430. Min Act: -0.1700
Data Index: 1835382 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3930. Min Range: -7.3930
Max Act: 6.0805. Min Act: -0.1700
Data Index: 6476924 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #19