Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2658 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8315. Min Range: -6.8315
Max Act: 6.8315. Min Act: -0.1700
Data Index: 454052 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8315. Min Range: -6.8315
Max Act: 6.8003. Min Act: -0.1700
Data Index: 7466506 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8315. Min Range: -6.8315
Max Act: 6.8003. Min Act: -0.1700
Data Index: 947151 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8315. Min Range: -6.8315
Max Act: 6.8003. Min Act: -0.1700
Data Index: 7348970 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8315. Min Range: -6.8315
Max Act: 6.7065. Min Act: -0.1700
Data Index: 5326946 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8315. Min Range: -6.8315
Max Act: 6.7065. Min Act: -0.1700
Data Index: 2657957 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8315. Min Range: -6.8315
Max Act: 6.6753. Min Act: -0.1700
Data Index: 8661560 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8315. Min Range: -6.8315
Max Act: 6.6440. Min Act: -0.1700
Data Index: 7466505 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8315. Min Range: -6.8315
Max Act: 6.6440. Min Act: -0.1700
Data Index: 7927626 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8315. Min Range: -6.8315
Max Act: 6.6440. Min Act: -0.1700
Data Index: 6992364 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8315. Min Range: -6.8315
Max Act: 6.6440. Min Act: -0.1700
Data Index: 2027920 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8315. Min Range: -6.8315
Max Act: 6.6128. Min Act: -0.1700
Data Index: 4830577 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8315. Min Range: -6.8315
Max Act: 6.6128. Min Act: -0.1700
Data Index: 134867 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8315. Min Range: -6.8315
Max Act: 6.5503. Min Act: -0.1700
Data Index: 7771997 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8315. Min Range: -6.8315
Max Act: 6.5503. Min Act: -0.1700
Data Index: 2704308 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8315. Min Range: -6.8315
Max Act: 6.5503. Min Act: -0.1700
Data Index: 5823749 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8315. Min Range: -6.8315
Max Act: 6.5190. Min Act: -0.1700
Data Index: 6386695 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8315. Min Range: -6.8315
Max Act: 6.4565. Min Act: -0.1700
Data Index: 437863 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8315. Min Range: -6.8315
Max Act: 6.4565. Min Act: -0.1700
Data Index: 2999061 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8315. Min Range: -6.8315
Max Act: 6.4253. Min Act: -0.1700
Data Index: 1693767 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #19