Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3590 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7853. Min Range: -5.7853
Max Act: 5.7853. Min Act: -0.1700
Data Index: 1569057 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7853. Min Range: -5.7853
Max Act: 5.6603. Min Act: -0.1700
Data Index: 7106921 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7853. Min Range: -5.7853
Max Act: 5.6603. Min Act: -0.1700
Data Index: 5620180 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7853. Min Range: -5.7853
Max Act: 5.5666. Min Act: -0.1700
Data Index: 3603065 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7853. Min Range: -5.7853
Max Act: 5.5353. Min Act: -0.1700
Data Index: 8758809 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7853. Min Range: -5.7853
Max Act: 5.5353. Min Act: -0.1700
Data Index: 101293 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7853. Min Range: -5.7853
Max Act: 5.5041. Min Act: -0.1700
Data Index: 4359341 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7853. Min Range: -5.7853
Max Act: 5.5041. Min Act: -0.1700
Data Index: 2438345 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7853. Min Range: -5.7853
Max Act: 5.5041. Min Act: -0.1700
Data Index: 5381432 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7853. Min Range: -5.7853
Max Act: 5.4728. Min Act: -0.1700
Data Index: 722579 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7853. Min Range: -5.7853
Max Act: 5.4103. Min Act: -0.1700
Data Index: 1734623 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7853. Min Range: -5.7853
Max Act: 5.4103. Min Act: -0.1700
Data Index: 1257051 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7853. Min Range: -5.7853
Max Act: 5.4103. Min Act: -0.1700
Data Index: 1531635 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7853. Min Range: -5.7853
Max Act: 5.3791. Min Act: -0.1700
Data Index: 6016027 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7853. Min Range: -5.7853
Max Act: 5.3791. Min Act: -0.1700
Data Index: 3328671 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7853. Min Range: -5.7853
Max Act: 5.3791. Min Act: -0.1700
Data Index: 8455211 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7853. Min Range: -5.7853
Max Act: 5.3791. Min Act: -0.1700
Data Index: 7405087 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7853. Min Range: -5.7853
Max Act: 5.3478. Min Act: -0.1700
Data Index: 1920992 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7853. Min Range: -5.7853
Max Act: 5.3478. Min Act: -0.1700
Data Index: 8507187 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7853. Min Range: -5.7853
Max Act: 5.3478. Min Act: -0.1700
Data Index: 8373424 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #19