Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4416 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9454. Min Range: -7.9454
Max Act: 7.9454. Min Act: -0.1700
Data Index: 7017784 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9454. Min Range: -7.9454
Max Act: 7.7267. Min Act: -0.1700
Data Index: 7252525 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9454. Min Range: -7.9454
Max Act: 7.6642. Min Act: -0.1700
Data Index: 4243515 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9454. Min Range: -7.9454
Max Act: 7.3829. Min Act: -0.1700
Data Index: 1574794 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9454. Min Range: -7.9454
Max Act: 7.3204. Min Act: -0.1700
Data Index: 7418855 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9454. Min Range: -7.9454
Max Act: 7.2579. Min Act: -0.1700
Data Index: 7698577 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9454. Min Range: -7.9454
Max Act: 7.1642. Min Act: -0.1700
Data Index: 185591 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9454. Min Range: -7.9454
Max Act: 7.1642. Min Act: -0.1700
Data Index: 1710209 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9454. Min Range: -7.9454
Max Act: 7.1017. Min Act: -0.1700
Data Index: 3327196 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9454. Min Range: -7.9454
Max Act: 7.1642. Min Act: -0.1700
Data Index: 5276535 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9454. Min Range: -7.9454
Max Act: 7.1329. Min Act: -0.1700
Data Index: 3936285 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9454. Min Range: -7.9454
Max Act: 7.0704. Min Act: -0.1700
Data Index: 3919216 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9454. Min Range: -7.9454
Max Act: 7.0704. Min Act: -0.1700
Data Index: 286016 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9454. Min Range: -7.9454
Max Act: 7.0392. Min Act: -0.1700
Data Index: 8651527 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9454. Min Range: -7.9454
Max Act: 6.9767. Min Act: -0.1700
Data Index: 2669461 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9454. Min Range: -7.9454
Max Act: 6.9142. Min Act: -0.1700
Data Index: 1850005 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9454. Min Range: -7.9454
Max Act: 6.9767. Min Act: -0.1700
Data Index: 2804970 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9454. Min Range: -7.9454
Max Act: 6.9142. Min Act: -0.1700
Data Index: 7036299 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9454. Min Range: -7.9454
Max Act: 6.8829. Min Act: -0.1700
Data Index: 7031215 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9454. Min Range: -7.9454
Max Act: 6.8829. Min Act: -0.1700
Data Index: 5900740 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #19