Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5780 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9995. Min Range: -5.9995
Max Act: 5.9995. Min Act: -0.1700
Data Index: 6011824 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9995. Min Range: -5.9995
Max Act: 5.9682. Min Act: -0.1700
Data Index: 2879469 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9995. Min Range: -5.9995
Max Act: 5.9682. Min Act: -0.1700
Data Index: 1200816 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9995. Min Range: -5.9995
Max Act: 5.8432. Min Act: -0.1700
Data Index: 6653281 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9995. Min Range: -5.9995
Max Act: 5.8432. Min Act: -0.1700
Data Index: 6646419 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9995. Min Range: -5.9995
Max Act: 5.8120. Min Act: -0.1700
Data Index: 8385433 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9995. Min Range: -5.9995
Max Act: 5.8120. Min Act: -0.1700
Data Index: 344310 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9995. Min Range: -5.9995
Max Act: 5.7807. Min Act: -0.1700
Data Index: 3061605 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9995. Min Range: -5.9995
Max Act: 5.7807. Min Act: -0.1700
Data Index: 5640868 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9995. Min Range: -5.9995
Max Act: 5.7495. Min Act: -0.1700
Data Index: 6871359 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9995. Min Range: -5.9995
Max Act: 5.7182. Min Act: -0.1700
Data Index: 1199136 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9995. Min Range: -5.9995
Max Act: 5.7182. Min Act: -0.1700
Data Index: 4626052 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9995. Min Range: -5.9995
Max Act: 5.7182. Min Act: -0.1700
Data Index: 8696742 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9995. Min Range: -5.9995
Max Act: 5.7182. Min Act: -0.1700
Data Index: 571274 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9995. Min Range: -5.9995
Max Act: 5.6870. Min Act: -0.1700
Data Index: 2103943 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9995. Min Range: -5.9995
Max Act: 5.6870. Min Act: -0.1700
Data Index: 5385961 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9995. Min Range: -5.9995
Max Act: 5.7182. Min Act: -0.1700
Data Index: 6772437 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9995. Min Range: -5.9995
Max Act: 5.6870. Min Act: -0.1700
Data Index: 7469911 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9995. Min Range: -5.9995
Max Act: 5.6870. Min Act: -0.1700
Data Index: 4010088 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9995. Min Range: -5.9995
Max Act: 5.6870. Min Act: -0.1700
Data Index: 4062312 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #19