Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4548 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7426. Min Range: -5.7426
Max Act: 5.7426. Min Act: -0.1700
Data Index: 8151658 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7426. Min Range: -5.7426
Max Act: 5.5551. Min Act: -0.1700
Data Index: 4804791 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7426. Min Range: -5.7426
Max Act: 5.4614. Min Act: -0.1700
Data Index: 477686 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7426. Min Range: -5.7426
Max Act: 5.3989. Min Act: -0.1700
Data Index: 7770450 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7426. Min Range: -5.7426
Max Act: 5.3676. Min Act: -0.1700
Data Index: 3829951 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7426. Min Range: -5.7426
Max Act: 5.3051. Min Act: -0.1700
Data Index: 7179536 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7426. Min Range: -5.7426
Max Act: 5.2739. Min Act: -0.1700
Data Index: 8157253 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7426. Min Range: -5.7426
Max Act: 5.2426. Min Act: -0.1700
Data Index: 3785113 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7426. Min Range: -5.7426
Max Act: 5.2426. Min Act: -0.1700
Data Index: 4142192 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7426. Min Range: -5.7426
Max Act: 5.2114. Min Act: -0.1700
Data Index: 5170575 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7426. Min Range: -5.7426
Max Act: 5.2114. Min Act: -0.1700
Data Index: 3882791 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7426. Min Range: -5.7426
Max Act: 5.1801. Min Act: -0.1700
Data Index: 4337973 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7426. Min Range: -5.7426
Max Act: 5.1489. Min Act: -0.1700
Data Index: 6774328 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7426. Min Range: -5.7426
Max Act: 5.1489. Min Act: -0.1700
Data Index: 2290909 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7426. Min Range: -5.7426
Max Act: 5.1489. Min Act: -0.1700
Data Index: 2027507 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7426. Min Range: -5.7426
Max Act: 5.1176. Min Act: -0.1700
Data Index: 8391057 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7426. Min Range: -5.7426
Max Act: 5.1176. Min Act: -0.1700
Data Index: 7956551 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7426. Min Range: -5.7426
Max Act: 5.1176. Min Act: -0.1700
Data Index: 6788015 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7426. Min Range: -5.7426
Max Act: 5.1176. Min Act: -0.1700
Data Index: 7756565 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7426. Min Range: -5.7426
Max Act: 5.0864. Min Act: -0.1700
Data Index: 6840084 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #19