Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2851 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0896. Min Range: -9.0896
Max Act: 9.0896. Min Act: -0.1700
Data Index: 1090029 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0896. Min Range: -9.0896
Max Act: 9.0271. Min Act: -0.1700
Data Index: 1090022 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0896. Min Range: -9.0896
Max Act: 8.7771. Min Act: -0.1700
Data Index: 4455303 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0896. Min Range: -9.0896
Max Act: 8.3396. Min Act: -0.1700
Data Index: 1387666 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0896. Min Range: -9.0896
Max Act: 8.2146. Min Act: -0.1700
Data Index: 6222812 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0896. Min Range: -9.0896
Max Act: 8.2146. Min Act: -0.1700
Data Index: 4776504 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0896. Min Range: -9.0896
Max Act: 8.2146. Min Act: -0.1700
Data Index: 6222808 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0896. Min Range: -9.0896
Max Act: 8.1521. Min Act: -0.1700
Data Index: 6222807 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0896. Min Range: -9.0896
Max Act: 8.1521. Min Act: -0.1700
Data Index: 3547953 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0896. Min Range: -9.0896
Max Act: 8.1521. Min Act: -0.1700
Data Index: 2533217 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0896. Min Range: -9.0896
Max Act: 8.2146. Min Act: -0.1700
Data Index: 5108780 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0896. Min Range: -9.0896
Max Act: 8.1521. Min Act: -0.1700
Data Index: 8285485 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0896. Min Range: -9.0896
Max Act: 8.1521. Min Act: -0.1700
Data Index: 8523195 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0896. Min Range: -9.0896
Max Act: 8.1208. Min Act: -0.1700
Data Index: 5108773 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0896. Min Range: -9.0896
Max Act: 8.1208. Min Act: -0.1700
Data Index: 6556190 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0896. Min Range: -9.0896
Max Act: 8.0583. Min Act: -0.1700
Data Index: 4457432 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0896. Min Range: -9.0896
Max Act: 8.0896. Min Act: -0.1700
Data Index: 4776518 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0896. Min Range: -9.0896
Max Act: 8.0583. Min Act: -0.1700
Data Index: 7353674 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0896. Min Range: -9.0896
Max Act: 8.1208. Min Act: -0.1700
Data Index: 6018338 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0896. Min Range: -9.0896
Max Act: 8.0271. Min Act: -0.1700
Data Index: 6235742 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19