Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1840 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5419. Min Range: -8.5419
Max Act: 8.5419. Min Act: -0.1700
Data Index: 2245340 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5419. Min Range: -8.5419
Max Act: 8.5419. Min Act: -0.1700
Data Index: 8602916 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5419. Min Range: -8.5419
Max Act: 7.7919. Min Act: -0.1700
Data Index: 1382368 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5419. Min Range: -8.5419
Max Act: 7.6669. Min Act: -0.1700
Data Index: 1391345 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5419. Min Range: -8.5419
Max Act: 7.6669. Min Act: -0.1700
Data Index: 4710502 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5419. Min Range: -8.5419
Max Act: 7.6981. Min Act: -0.1700
Data Index: 3234492 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5419. Min Range: -8.5419
Max Act: 7.6356. Min Act: -0.1700
Data Index: 116199 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5419. Min Range: -8.5419
Max Act: 7.6044. Min Act: -0.1700
Data Index: 3401128 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5419. Min Range: -8.5419
Max Act: 7.6356. Min Act: -0.1700
Data Index: 2520681 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5419. Min Range: -8.5419
Max Act: 7.6356. Min Act: -0.1700
Data Index: 5693504 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5419. Min Range: -8.5419
Max Act: 7.6356. Min Act: -0.1700
Data Index: 8710974 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5419. Min Range: -8.5419
Max Act: 7.6356. Min Act: -0.1700
Data Index: 8582566 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5419. Min Range: -8.5419
Max Act: 7.5731. Min Act: -0.1700
Data Index: 2088207 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5419. Min Range: -8.5419
Max Act: 7.5731. Min Act: -0.1700
Data Index: 5776935 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5419. Min Range: -8.5419
Max Act: 7.5731. Min Act: -0.1700
Data Index: 527609 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5419. Min Range: -8.5419
Max Act: 7.5731. Min Act: -0.1700
Data Index: 764534 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5419. Min Range: -8.5419
Max Act: 7.5106. Min Act: -0.1700
Data Index: 3156946 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5419. Min Range: -8.5419
Max Act: 7.5419. Min Act: -0.1700
Data Index: 7218305 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5419. Min Range: -8.5419
Max Act: 7.4794. Min Act: -0.1700
Data Index: 2896260 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5419. Min Range: -8.5419
Max Act: 7.4481. Min Act: -0.1700
Data Index: 5802134 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #19