Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5402 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3386. Min Range: -5.3386
Max Act: 5.3386. Min Act: -0.1700
Data Index: 2178324 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3386. Min Range: -5.3386
Max Act: 5.2761. Min Act: -0.1700
Data Index: 2880805 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3386. Min Range: -5.3386
Max Act: 5.2761. Min Act: -0.1700
Data Index: 4132112 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3386. Min Range: -5.3386
Max Act: 5.2136. Min Act: -0.1700
Data Index: 5267139 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3386. Min Range: -5.3386
Max Act: 5.1824. Min Act: -0.1700
Data Index: 7448816 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3386. Min Range: -5.3386
Max Act: 5.1511. Min Act: -0.1700
Data Index: 5326253 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3386. Min Range: -5.3386
Max Act: 5.1511. Min Act: -0.1700
Data Index: 3568741 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3386. Min Range: -5.3386
Max Act: 5.1511. Min Act: -0.1700
Data Index: 5086662 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3386. Min Range: -5.3386
Max Act: 5.1511. Min Act: -0.1700
Data Index: 1702337 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3386. Min Range: -5.3386
Max Act: 5.1511. Min Act: -0.1700
Data Index: 6375708 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3386. Min Range: -5.3386
Max Act: 5.1511. Min Act: -0.1700
Data Index: 1986458 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3386. Min Range: -5.3386
Max Act: 5.1511. Min Act: -0.1700
Data Index: 1176725 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3386. Min Range: -5.3386
Max Act: 5.1199. Min Act: -0.1700
Data Index: 4992459 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3386. Min Range: -5.3386
Max Act: 5.1199. Min Act: -0.1700
Data Index: 3445391 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3386. Min Range: -5.3386
Max Act: 5.1199. Min Act: -0.1700
Data Index: 5622173 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3386. Min Range: -5.3386
Max Act: 5.1199. Min Act: -0.1700
Data Index: 3046470 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3386. Min Range: -5.3386
Max Act: 5.1199. Min Act: -0.1700
Data Index: 1763826 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3386. Min Range: -5.3386
Max Act: 5.0886. Min Act: -0.1700
Data Index: 4098586 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3386. Min Range: -5.3386
Max Act: 5.0886. Min Act: -0.1700
Data Index: 1369088 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3386. Min Range: -5.3386
Max Act: 5.0886. Min Act: -0.1700
Data Index: 693072 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #19