Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 277 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7882. Min Range: -6.7882
Max Act: 6.7882. Min Act: -0.1700
Data Index: 4920378 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7882. Min Range: -6.7882
Max Act: 6.6319. Min Act: -0.1700
Data Index: 2414025 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7882. Min Range: -6.7882
Max Act: 6.6007. Min Act: -0.1700
Data Index: 5350968 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7882. Min Range: -6.7882
Max Act: 6.3194. Min Act: -0.1700
Data Index: 6049014 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7882. Min Range: -6.7882
Max Act: 6.3194. Min Act: -0.1700
Data Index: 4632680 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7882. Min Range: -6.7882
Max Act: 6.2569. Min Act: -0.1700
Data Index: 7183130 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7882. Min Range: -6.7882
Max Act: 6.2257. Min Act: -0.1700
Data Index: 3632604 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7882. Min Range: -6.7882
Max Act: 6.1632. Min Act: -0.1700
Data Index: 8721096 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7882. Min Range: -6.7882
Max Act: 6.1632. Min Act: -0.1700
Data Index: 5064473 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7882. Min Range: -6.7882
Max Act: 6.1632. Min Act: -0.1700
Data Index: 587628 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7882. Min Range: -6.7882
Max Act: 6.1319. Min Act: -0.1700
Data Index: 392930 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7882. Min Range: -6.7882
Max Act: 6.1007. Min Act: -0.1700
Data Index: 3909866 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7882. Min Range: -6.7882
Max Act: 6.1319. Min Act: -0.1700
Data Index: 7302779 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7882. Min Range: -6.7882
Max Act: 6.1632. Min Act: -0.1700
Data Index: 763242 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7882. Min Range: -6.7882
Max Act: 6.1007. Min Act: -0.1700
Data Index: 3157512 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7882. Min Range: -6.7882
Max Act: 6.1007. Min Act: -0.1700
Data Index: 113063 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7882. Min Range: -6.7882
Max Act: 6.1007. Min Act: -0.1700
Data Index: 2502838 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7882. Min Range: -6.7882
Max Act: 6.1319. Min Act: -0.1700
Data Index: 8680096 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7882. Min Range: -6.7882
Max Act: 6.1007. Min Act: -0.1700
Data Index: 7837394 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7882. Min Range: -6.7882
Max Act: 6.0694. Min Act: -0.1700
Data Index: 2577582 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #19