Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5108 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.6066. Min Range: -9.6066
Max Act: 9.6066. Min Act: -0.1700
Data Index: 354784 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6066. Min Range: -9.6066
Max Act: 9.4191. Min Act: -0.1700
Data Index: 4968679 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6066. Min Range: -9.6066
Max Act: 9.2941. Min Act: -0.1700
Data Index: 1000055 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6066. Min Range: -9.6066
Max Act: 9.4191. Min Act: -0.1700
Data Index: 6219251 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6066. Min Range: -9.6066
Max Act: 9.2941. Min Act: -0.1700
Data Index: 6023644 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6066. Min Range: -9.6066
Max Act: 9.2316. Min Act: -0.1700
Data Index: 1007729 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6066. Min Range: -9.6066
Max Act: 9.1066. Min Act: -0.1700
Data Index: 1187582 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6066. Min Range: -9.6066
Max Act: 9.1066. Min Act: -0.1700
Data Index: 359941 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6066. Min Range: -9.6066
Max Act: 9.1066. Min Act: -0.1700
Data Index: 7753229 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6066. Min Range: -9.6066
Max Act: 9.1066. Min Act: -0.1700
Data Index: 3718786 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6066. Min Range: -9.6066
Max Act: 9.1066. Min Act: -0.1700
Data Index: 8402794 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6066. Min Range: -9.6066
Max Act: 8.9816. Min Act: -0.1700
Data Index: 3998594 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6066. Min Range: -9.6066
Max Act: 8.9191. Min Act: -0.1700
Data Index: 263563 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6066. Min Range: -9.6066
Max Act: 8.8566. Min Act: -0.1700
Data Index: 7106388 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6066. Min Range: -9.6066
Max Act: 8.9191. Min Act: -0.1700
Data Index: 2237966 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6066. Min Range: -9.6066
Max Act: 8.7941. Min Act: -0.1700
Data Index: 8438088 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6066. Min Range: -9.6066
Max Act: 8.8566. Min Act: -0.1700
Data Index: 4731212 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6066. Min Range: -9.6066
Max Act: 8.7941. Min Act: -0.1700
Data Index: 1929250 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6066. Min Range: -9.6066
Max Act: 8.7941. Min Act: -0.1700
Data Index: 2180920 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6066. Min Range: -9.6066
Max Act: 8.7316. Min Act: -0.1700
Data Index: 6741412 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #19