Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2807 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4697. Min Range: -3.4697
Max Act: 3.4697. Min Act: -0.1700
Data Index: 5194299 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4697. Min Range: -3.4697
Max Act: 3.3600. Min Act: -0.1700
Data Index: 1830973 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4697. Min Range: -3.4697
Max Act: 3.3443. Min Act: -0.1700
Data Index: 3034644 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4697. Min Range: -3.4697
Max Act: 3.3129. Min Act: -0.1700
Data Index: 5344138 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4697. Min Range: -3.4697
Max Act: 3.2658. Min Act: -0.1700
Data Index: 2721717 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4697. Min Range: -3.4697
Max Act: 3.2030. Min Act: -0.1700
Data Index: 1711185 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4697. Min Range: -3.4697
Max Act: 3.1715. Min Act: -0.1700
Data Index: 5415474 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4697. Min Range: -3.4697
Max Act: 3.1558. Min Act: -0.1700
Data Index: 7645804 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4697. Min Range: -3.4697
Max Act: 3.1715. Min Act: -0.1700
Data Index: 4212122 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4697. Min Range: -3.4697
Max Act: 3.1085. Min Act: -0.1700
Data Index: 3432868 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4697. Min Range: -3.4697
Max Act: 3.0770. Min Act: -0.1700
Data Index: 8037029 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4697. Min Range: -3.4697
Max Act: 3.0612. Min Act: -0.1700
Data Index: 6692921 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4697. Min Range: -3.4697
Max Act: 3.0770. Min Act: -0.1700
Data Index: 5967281 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4697. Min Range: -3.4697
Max Act: 3.0770. Min Act: -0.1700
Data Index: 3449865 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4697. Min Range: -3.4697
Max Act: 3.0770. Min Act: -0.1700
Data Index: 23238 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4697. Min Range: -3.4697
Max Act: 3.0612. Min Act: -0.1700
Data Index: 1943177 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4697. Min Range: -3.4697
Max Act: 3.0297. Min Act: -0.1700
Data Index: 5771793 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4697. Min Range: -3.4697
Max Act: 3.0454. Min Act: -0.1700
Data Index: 3380177 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4697. Min Range: -3.4697
Max Act: 3.0139. Min Act: -0.1700
Data Index: 2752216 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4697. Min Range: -3.4697
Max Act: 3.0454. Min Act: -0.1700
Data Index: 3459364 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #19