Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5026 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5636. Min Range: -6.5636
Max Act: 6.5636. Min Act: -0.1700
Data Index: 1168304 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5636. Min Range: -6.5636
Max Act: 6.4386. Min Act: -0.1700
Data Index: 1457864 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5636. Min Range: -6.5636
Max Act: 6.3761. Min Act: -0.1700
Data Index: 6812172 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5636. Min Range: -6.5636
Max Act: 6.3761. Min Act: -0.1700
Data Index: 506656 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5636. Min Range: -6.5636
Max Act: 6.3136. Min Act: -0.1700
Data Index: 3034602 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5636. Min Range: -6.5636
Max Act: 6.3136. Min Act: -0.1697
Data Index: 1429011 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5636. Min Range: -6.5636
Max Act: 6.2823. Min Act: -0.1700
Data Index: 5709906 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5636. Min Range: -6.5636
Max Act: 6.2823. Min Act: -0.1700
Data Index: 1639966 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5636. Min Range: -6.5636
Max Act: 6.2823. Min Act: -0.1700
Data Index: 1120899 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5636. Min Range: -6.5636
Max Act: 6.2511. Min Act: -0.1700
Data Index: 1457870 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5636. Min Range: -6.5636
Max Act: 6.2511. Min Act: -0.1700
Data Index: 1886315 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5636. Min Range: -6.5636
Max Act: 6.2511. Min Act: -0.1700
Data Index: 7599087 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5636. Min Range: -6.5636
Max Act: 6.2198. Min Act: -0.1700
Data Index: 8411976 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5636. Min Range: -6.5636
Max Act: 6.2511. Min Act: -0.1700
Data Index: 6305739 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5636. Min Range: -6.5636
Max Act: 6.1886. Min Act: -0.1700
Data Index: 8181789 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5636. Min Range: -6.5636
Max Act: 6.1886. Min Act: -0.1697
Data Index: 647912 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5636. Min Range: -6.5636
Max Act: 6.1886. Min Act: -0.1700
Data Index: 4516548 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5636. Min Range: -6.5636
Max Act: 6.1886. Min Act: -0.1700
Data Index: 2745258 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5636. Min Range: -6.5636
Max Act: 6.1886. Min Act: -0.1700
Data Index: 3044526 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5636. Min Range: -6.5636
Max Act: 6.1573. Min Act: -0.1700
Data Index: 4490003 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #19