Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3118 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1759. Min Range: -8.1759
Max Act: 8.1759. Min Act: -0.1700
Data Index: 1753462 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1759. Min Range: -8.1759
Max Act: 8.1134. Min Act: -0.1700
Data Index: 5112451 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1759. Min Range: -8.1759
Max Act: 8.1134. Min Act: -0.1700
Data Index: 6272751 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1759. Min Range: -8.1759
Max Act: 8.0509. Min Act: -0.1700
Data Index: 4743253 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1759. Min Range: -8.1759
Max Act: 8.0197. Min Act: -0.1700
Data Index: 104372 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1759. Min Range: -8.1759
Max Act: 8.0197. Min Act: -0.1700
Data Index: 1634746 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1759. Min Range: -8.1759
Max Act: 8.0197. Min Act: -0.1700
Data Index: 1959066 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1759. Min Range: -8.1759
Max Act: 7.9884. Min Act: -0.1700
Data Index: 3796321 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1759. Min Range: -8.1759
Max Act: 7.9884. Min Act: -0.1700
Data Index: 7405527 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1759. Min Range: -8.1759
Max Act: 7.9884. Min Act: -0.1700
Data Index: 8703848 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1759. Min Range: -8.1759
Max Act: 8.0197. Min Act: -0.1700
Data Index: 8326932 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1759. Min Range: -8.1759
Max Act: 7.9884. Min Act: -0.1700
Data Index: 234551 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1759. Min Range: -8.1759
Max Act: 7.9884. Min Act: -0.1700
Data Index: 6584792 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1759. Min Range: -8.1759
Max Act: 7.9884. Min Act: -0.1700
Data Index: 3780221 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1759. Min Range: -8.1759
Max Act: 7.9259. Min Act: -0.1700
Data Index: 2164219 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1759. Min Range: -8.1759
Max Act: 7.9259. Min Act: -0.1700
Data Index: 2049901 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1759. Min Range: -8.1759
Max Act: 7.8947. Min Act: -0.1700
Data Index: 8240763 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1759. Min Range: -8.1759
Max Act: 7.8947. Min Act: -0.1700
Data Index: 1109156 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1759. Min Range: -8.1759
Max Act: 7.8322. Min Act: -0.1700
Data Index: 5523017 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1759. Min Range: -8.1759
Max Act: 7.8322. Min Act: -0.1700
Data Index: 4617040 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #19