Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3063 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9760. Min Range: -3.9760
Max Act: 3.9760. Min Act: -0.1700
Data Index: 8567816 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9760. Min Range: -3.9760
Max Act: 3.7884. Min Act: -0.1700
Data Index: 6708279 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9760. Min Range: -3.9760
Max Act: 3.7571. Min Act: -0.1700
Data Index: 4018711 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9760. Min Range: -3.9760
Max Act: 3.7571. Min Act: -0.1700
Data Index: 1645366 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9760. Min Range: -3.9760
Max Act: 3.7258. Min Act: -0.1700
Data Index: 4814828 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9760. Min Range: -3.9760
Max Act: 3.7102. Min Act: -0.1700
Data Index: 1875252 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9760. Min Range: -3.9760
Max Act: 3.6789. Min Act: -0.1700
Data Index: 6830458 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9760. Min Range: -3.9760
Max Act: 3.6476. Min Act: -0.1700
Data Index: 573812 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9760. Min Range: -3.9760
Max Act: 3.6632. Min Act: -0.1700
Data Index: 1929964 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9760. Min Range: -3.9760
Max Act: 3.6163. Min Act: -0.1700
Data Index: 6627133 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9760. Min Range: -3.9760
Max Act: 3.6006. Min Act: -0.1700
Data Index: 641528 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9760. Min Range: -3.9760
Max Act: 3.5537. Min Act: -0.1700
Data Index: 7475933 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9760. Min Range: -3.9760
Max Act: 3.5537. Min Act: -0.1700
Data Index: 282391 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9760. Min Range: -3.9760
Max Act: 3.5224. Min Act: -0.1700
Data Index: 7418465 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9760. Min Range: -3.9760
Max Act: 3.5067. Min Act: -0.1700
Data Index: 6995368 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9760. Min Range: -3.9760
Max Act: 3.5067. Min Act: -0.1700
Data Index: 1219576 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9760. Min Range: -3.9760
Max Act: 3.5067. Min Act: -0.1700
Data Index: 4134534 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9760. Min Range: -3.9760
Max Act: 3.4597. Min Act: -0.1700
Data Index: 1186442 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9760. Min Range: -3.9760
Max Act: 3.4910. Min Act: -0.1700
Data Index: 4974766 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9760. Min Range: -3.9760
Max Act: 3.4754. Min Act: -0.1700
Data Index: 3605908 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #19