Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 623 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6676. Min Range: -7.6676
Max Act: 7.6676. Min Act: -0.1700
Data Index: 5252659 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6676. Min Range: -7.6676
Max Act: 7.5426. Min Act: -0.1700
Data Index: 2388165 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6676. Min Range: -7.6676
Max Act: 7.5426. Min Act: -0.1700
Data Index: 6712387 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6676. Min Range: -7.6676
Max Act: 7.3863. Min Act: -0.1700
Data Index: 6551999 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6676. Min Range: -7.6676
Max Act: 7.3551. Min Act: -0.1700
Data Index: 5594940 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6676. Min Range: -7.6676
Max Act: 7.3238. Min Act: -0.1700
Data Index: 5156053 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6676. Min Range: -7.6676
Max Act: 7.2926. Min Act: -0.1700
Data Index: 3756573 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6676. Min Range: -7.6676
Max Act: 7.2613. Min Act: -0.1700
Data Index: 264294 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6676. Min Range: -7.6676
Max Act: 7.2301. Min Act: -0.1700
Data Index: 6469352 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6676. Min Range: -7.6676
Max Act: 7.1988. Min Act: -0.1700
Data Index: 6181906 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6676. Min Range: -7.6676
Max Act: 7.1988. Min Act: -0.1700
Data Index: 7501343 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6676. Min Range: -7.6676
Max Act: 7.1363. Min Act: -0.1700
Data Index: 7926076 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6676. Min Range: -7.6676
Max Act: 7.1051. Min Act: -0.1700
Data Index: 2326048 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6676. Min Range: -7.6676
Max Act: 7.1051. Min Act: -0.1700
Data Index: 8810521 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6676. Min Range: -7.6676
Max Act: 7.0738. Min Act: -0.1700
Data Index: 3750938 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6676. Min Range: -7.6676
Max Act: 7.0113. Min Act: -0.1700
Data Index: 697074 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6676. Min Range: -7.6676
Max Act: 7.0426. Min Act: -0.1700
Data Index: 4806764 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6676. Min Range: -7.6676
Max Act: 7.0113. Min Act: -0.1700
Data Index: 2862364 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6676. Min Range: -7.6676
Max Act: 6.9801. Min Act: -0.1700
Data Index: 4643826 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6676. Min Range: -7.6676
Max Act: 6.9801. Min Act: -0.1700
Data Index: 6806009 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #19