Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5544 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9780. Min Range: -5.9780
Max Act: 5.9780. Min Act: -0.1700
Data Index: 7616780 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9780. Min Range: -5.9780
Max Act: 5.9780. Min Act: -0.1699
Data Index: 3583579 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9780. Min Range: -5.9780
Max Act: 5.8843. Min Act: -0.1700
Data Index: 6971463 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9780. Min Range: -5.9780
Max Act: 5.8530. Min Act: -0.1700
Data Index: 3411990 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9780. Min Range: -5.9780
Max Act: 5.8530. Min Act: -0.1699
Data Index: 4064351 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9780. Min Range: -5.9780
Max Act: 5.8530. Min Act: -0.1700
Data Index: 410324 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9780. Min Range: -5.9780
Max Act: 5.8218. Min Act: -0.1700
Data Index: 52788 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9780. Min Range: -5.9780
Max Act: 5.7593. Min Act: -0.1700
Data Index: 4709275 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9780. Min Range: -5.9780
Max Act: 5.7593. Min Act: -0.1700
Data Index: 3637026 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9780. Min Range: -5.9780
Max Act: 5.7280. Min Act: -0.1700
Data Index: 2240541 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9780. Min Range: -5.9780
Max Act: 5.7280. Min Act: -0.1700
Data Index: 5391057 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9780. Min Range: -5.9780
Max Act: 5.7280. Min Act: -0.1700
Data Index: 2845854 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9780. Min Range: -5.9780
Max Act: 5.7280. Min Act: -0.1700
Data Index: 8714339 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9780. Min Range: -5.9780
Max Act: 5.6968. Min Act: -0.1700
Data Index: 1353186 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9780. Min Range: -5.9780
Max Act: 5.6968. Min Act: -0.1700
Data Index: 3655938 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9780. Min Range: -5.9780
Max Act: 5.6968. Min Act: -0.1700
Data Index: 8095989 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9780. Min Range: -5.9780
Max Act: 5.6968. Min Act: -0.1700
Data Index: 472235 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9780. Min Range: -5.9780
Max Act: 5.6655. Min Act: -0.1699
Data Index: 2481267 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9780. Min Range: -5.9780
Max Act: 5.6343. Min Act: -0.1700
Data Index: 496704 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9780. Min Range: -5.9780
Max Act: 5.6655. Min Act: -0.1700
Data Index: 736610 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #19