Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 738 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.1625. Min Range: -7.1625
Max Act: 7.1625. Min Act: -0.1700
Data Index: 7216784 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1625. Min Range: -7.1625
Max Act: 7.1312. Min Act: -0.1700
Data Index: 5651871 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1625. Min Range: -7.1625
Max Act: 7.0687. Min Act: -0.1700
Data Index: 3958232 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1625. Min Range: -7.1625
Max Act: 7.0375. Min Act: -0.1700
Data Index: 8077857 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1625. Min Range: -7.1625
Max Act: 7.0062. Min Act: -0.1700
Data Index: 8109207 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1625. Min Range: -7.1625
Max Act: 6.9437. Min Act: -0.1700
Data Index: 210772 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1625. Min Range: -7.1625
Max Act: 6.9750. Min Act: -0.1700
Data Index: 8085269 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1625. Min Range: -7.1625
Max Act: 6.9437. Min Act: -0.1700
Data Index: 1013498 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1625. Min Range: -7.1625
Max Act: 6.8500. Min Act: -0.1700
Data Index: 6406998 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1625. Min Range: -7.1625
Max Act: 6.8187. Min Act: -0.1700
Data Index: 518040 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1625. Min Range: -7.1625
Max Act: 6.8187. Min Act: -0.1700
Data Index: 6911902 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1625. Min Range: -7.1625
Max Act: 6.7875. Min Act: -0.1700
Data Index: 7792705 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1625. Min Range: -7.1625
Max Act: 6.7562. Min Act: -0.1700
Data Index: 51751 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1625. Min Range: -7.1625
Max Act: 6.7562. Min Act: -0.1700
Data Index: 71352 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1625. Min Range: -7.1625
Max Act: 6.7875. Min Act: -0.1700
Data Index: 1040668 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1625. Min Range: -7.1625
Max Act: 6.7875. Min Act: -0.1700
Data Index: 4679703 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1625. Min Range: -7.1625
Max Act: 6.7250. Min Act: -0.1700
Data Index: 23750 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1625. Min Range: -7.1625
Max Act: 6.7562. Min Act: -0.1700
Data Index: 4093335 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1625. Min Range: -7.1625
Max Act: 6.7562. Min Act: -0.1700
Data Index: 2162409 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1625. Min Range: -7.1625
Max Act: 6.6937. Min Act: -0.1700
Data Index: 2934074 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #19