Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5307 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1093. Min Range: -8.1093
Max Act: 8.1093. Min Act: -0.1700
Data Index: 6664975 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1093. Min Range: -8.1093
Max Act: 7.6093. Min Act: -0.1700
Data Index: 7657856 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1093. Min Range: -8.1093
Max Act: 7.5781. Min Act: -0.1700
Data Index: 7070778 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1093. Min Range: -8.1093
Max Act: 7.5781. Min Act: -0.1700
Data Index: 7380164 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1093. Min Range: -8.1093
Max Act: 7.5156. Min Act: -0.1700
Data Index: 2368976 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1093. Min Range: -8.1093
Max Act: 7.4531. Min Act: -0.1700
Data Index: 7414546 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1093. Min Range: -8.1093
Max Act: 7.4218. Min Act: -0.1700
Data Index: 57481 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1093. Min Range: -8.1093
Max Act: 7.3906. Min Act: -0.1700
Data Index: 7678717 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1093. Min Range: -8.1093
Max Act: 7.3906. Min Act: -0.1700
Data Index: 3020434 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1093. Min Range: -8.1093
Max Act: 7.3593. Min Act: -0.1700
Data Index: 3726890 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1093. Min Range: -8.1093
Max Act: 7.3593. Min Act: -0.1700
Data Index: 3341060 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1093. Min Range: -8.1093
Max Act: 7.3281. Min Act: -0.1700
Data Index: 3057118 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1093. Min Range: -8.1093
Max Act: 7.3281. Min Act: -0.1700
Data Index: 3025853 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1093. Min Range: -8.1093
Max Act: 7.2656. Min Act: -0.1700
Data Index: 7488903 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1093. Min Range: -8.1093
Max Act: 7.2656. Min Act: -0.1700
Data Index: 5194523 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1093. Min Range: -8.1093
Max Act: 7.2968. Min Act: -0.1700
Data Index: 8130211 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1093. Min Range: -8.1093
Max Act: 7.2656. Min Act: -0.1700
Data Index: 7526199 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1093. Min Range: -8.1093
Max Act: 7.2343. Min Act: -0.1700
Data Index: 4211620 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1093. Min Range: -8.1093
Max Act: 7.1718. Min Act: -0.1700
Data Index: 3863247 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1093. Min Range: -8.1093
Max Act: 7.2031. Min Act: -0.1700
Data Index: 4365389 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #19