Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1924 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3257. Min Range: -7.3257
Max Act: 7.3257. Min Act: -0.1700
Data Index: 2998657 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3257. Min Range: -7.3257
Max Act: 7.2320. Min Act: -0.1700
Data Index: 5732268 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3257. Min Range: -7.3257
Max Act: 7.2320. Min Act: -0.1700
Data Index: 144036 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3257. Min Range: -7.3257
Max Act: 7.1382. Min Act: -0.1700
Data Index: 1727490 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3257. Min Range: -7.3257
Max Act: 7.0757. Min Act: -0.1700
Data Index: 4637219 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3257. Min Range: -7.3257
Max Act: 7.0757. Min Act: -0.1700
Data Index: 7440096 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3257. Min Range: -7.3257
Max Act: 7.0132. Min Act: -0.1700
Data Index: 1387581 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3257. Min Range: -7.3257
Max Act: 6.9820. Min Act: -0.1700
Data Index: 7961395 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3257. Min Range: -7.3257
Max Act: 6.9507. Min Act: -0.1700
Data Index: 712000 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3257. Min Range: -7.3257
Max Act: 6.9820. Min Act: -0.1700
Data Index: 7134695 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3257. Min Range: -7.3257
Max Act: 7.0132. Min Act: -0.1700
Data Index: 6170324 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3257. Min Range: -7.3257
Max Act: 6.9820. Min Act: -0.1700
Data Index: 3137646 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3257. Min Range: -7.3257
Max Act: 6.9195. Min Act: -0.1700
Data Index: 6997596 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3257. Min Range: -7.3257
Max Act: 6.8882. Min Act: -0.1700
Data Index: 1570938 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3257. Min Range: -7.3257
Max Act: 6.8570. Min Act: -0.1700
Data Index: 1955947 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3257. Min Range: -7.3257
Max Act: 6.8570. Min Act: -0.1700
Data Index: 4249377 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3257. Min Range: -7.3257
Max Act: 6.8882. Min Act: -0.1700
Data Index: 8753241 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3257. Min Range: -7.3257
Max Act: 6.8257. Min Act: -0.1700
Data Index: 3065223 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3257. Min Range: -7.3257
Max Act: 6.8257. Min Act: -0.1700
Data Index: 4247214 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3257. Min Range: -7.3257
Max Act: 6.8570. Min Act: -0.1700
Data Index: 7512953 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #19