Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3456 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6506. Min Range: -6.6506
Max Act: 6.6506. Min Act: -0.1700
Data Index: 1010015 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6506. Min Range: -6.6506
Max Act: 6.6193. Min Act: -0.1700
Data Index: 600700 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6506. Min Range: -6.6506
Max Act: 6.4006. Min Act: -0.1700
Data Index: 3906774 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6506. Min Range: -6.6506
Max Act: 6.3693. Min Act: -0.1700
Data Index: 2887897 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6506. Min Range: -6.6506
Max Act: 6.3693. Min Act: -0.1700
Data Index: 4885659 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6506. Min Range: -6.6506
Max Act: 6.3381. Min Act: -0.1700
Data Index: 5094265 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6506. Min Range: -6.6506
Max Act: 6.3381. Min Act: -0.1700
Data Index: 1170585 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6506. Min Range: -6.6506
Max Act: 6.3068. Min Act: -0.1700
Data Index: 7743401 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6506. Min Range: -6.6506
Max Act: 6.2756. Min Act: -0.1700
Data Index: 4885657 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6506. Min Range: -6.6506
Max Act: 6.2443. Min Act: -0.1700
Data Index: 1209617 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6506. Min Range: -6.6506
Max Act: 6.2443. Min Act: -0.1700
Data Index: 2887903 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6506. Min Range: -6.6506
Max Act: 6.2443. Min Act: -0.1700
Data Index: 7927942 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6506. Min Range: -6.6506
Max Act: 6.2443. Min Act: -0.1700
Data Index: 1298894 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6506. Min Range: -6.6506
Max Act: 6.2443. Min Act: -0.1700
Data Index: 4411042 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6506. Min Range: -6.6506
Max Act: 6.2131. Min Act: -0.1700
Data Index: 377411 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6506. Min Range: -6.6506
Max Act: 6.2131. Min Act: -0.1700
Data Index: 7218716 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6506. Min Range: -6.6506
Max Act: 6.2131. Min Act: -0.1700
Data Index: 4411043 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6506. Min Range: -6.6506
Max Act: 6.1818. Min Act: -0.1700
Data Index: 4189668 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6506. Min Range: -6.6506
Max Act: 6.1818. Min Act: -0.1700
Data Index: 4885655 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6506. Min Range: -6.6506
Max Act: 6.1818. Min Act: -0.1700
Data Index: 4291399 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #19