Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1113 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1604. Min Range: -6.1604
Max Act: 6.1604. Min Act: -0.1700
Data Index: 6616350 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1604. Min Range: -6.1604
Max Act: 6.0354. Min Act: -0.1700
Data Index: 3813787 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1604. Min Range: -6.1604
Max Act: 6.0042. Min Act: -0.1700
Data Index: 7233087 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1604. Min Range: -6.1604
Max Act: 6.0354. Min Act: -0.1700
Data Index: 4323683 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1604. Min Range: -6.1604
Max Act: 5.8167. Min Act: -0.1700
Data Index: 1540127 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1604. Min Range: -6.1604
Max Act: 5.8479. Min Act: -0.1700
Data Index: 7462029 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1604. Min Range: -6.1604
Max Act: 5.8167. Min Act: -0.1700
Data Index: 3813783 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1604. Min Range: -6.1604
Max Act: 5.6917. Min Act: -0.1700
Data Index: 141007 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1604. Min Range: -6.1604
Max Act: 5.8479. Min Act: -0.1700
Data Index: 6331346 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1604. Min Range: -6.1604
Max Act: 5.8167. Min Act: -0.1700
Data Index: 7440548 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1604. Min Range: -6.1604
Max Act: 5.7854. Min Act: -0.1700
Data Index: 1009132 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1604. Min Range: -6.1604
Max Act: 5.7542. Min Act: -0.1700
Data Index: 913824 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1604. Min Range: -6.1604
Max Act: 5.7854. Min Act: -0.1700
Data Index: 7543616 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1604. Min Range: -6.1604
Max Act: 5.6917. Min Act: -0.1700
Data Index: 4107481 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1604. Min Range: -6.1604
Max Act: 5.7542. Min Act: -0.1700
Data Index: 1188387 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1604. Min Range: -6.1604
Max Act: 5.7542. Min Act: -0.1700
Data Index: 6616355 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1604. Min Range: -6.1604
Max Act: 5.7854. Min Act: -0.1700
Data Index: 5802032 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1604. Min Range: -6.1604
Max Act: 5.7229. Min Act: -0.1700
Data Index: 4548317 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1604. Min Range: -6.1604
Max Act: 5.6292. Min Act: -0.1700
Data Index: 368060 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1604. Min Range: -6.1604
Max Act: 5.6604. Min Act: -0.1700
Data Index: 2768876 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #19