Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6194 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0608. Min Range: -6.0608
Max Act: 6.0608. Min Act: -0.1700
Data Index: 5053752 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0608. Min Range: -6.0608
Max Act: 5.9671. Min Act: -0.1700
Data Index: 7110826 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0608. Min Range: -6.0608
Max Act: 5.9358. Min Act: -0.1700
Data Index: 801488 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0608. Min Range: -6.0608
Max Act: 5.9358. Min Act: -0.1700
Data Index: 1121359 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0608. Min Range: -6.0608
Max Act: 5.9046. Min Act: -0.1700
Data Index: 4026284 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0608. Min Range: -6.0608
Max Act: 5.8733. Min Act: -0.1700
Data Index: 4267475 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0608. Min Range: -6.0608
Max Act: 5.8733. Min Act: -0.1700
Data Index: 4943159 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0608. Min Range: -6.0608
Max Act: 5.8421. Min Act: -0.1700
Data Index: 4752014 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0608. Min Range: -6.0608
Max Act: 5.8108. Min Act: -0.1700
Data Index: 5526024 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0608. Min Range: -6.0608
Max Act: 5.8108. Min Act: -0.1700
Data Index: 7870904 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0608. Min Range: -6.0608
Max Act: 5.7796. Min Act: -0.1700
Data Index: 8617620 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0608. Min Range: -6.0608
Max Act: 5.7796. Min Act: -0.1700
Data Index: 4879223 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0608. Min Range: -6.0608
Max Act: 5.7483. Min Act: -0.1700
Data Index: 2066974 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0608. Min Range: -6.0608
Max Act: 5.7483. Min Act: -0.1700
Data Index: 4920770 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0608. Min Range: -6.0608
Max Act: 5.7483. Min Act: -0.1700
Data Index: 5792381 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0608. Min Range: -6.0608
Max Act: 5.7171. Min Act: -0.1700
Data Index: 3954783 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0608. Min Range: -6.0608
Max Act: 5.7171. Min Act: -0.1700
Data Index: 1338883 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0608. Min Range: -6.0608
Max Act: 5.6858. Min Act: -0.1700
Data Index: 2212563 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0608. Min Range: -6.0608
Max Act: 5.7171. Min Act: -0.1700
Data Index: 1687711 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0608. Min Range: -6.0608
Max Act: 5.7171. Min Act: -0.1700
Data Index: 2464716 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #19