Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3979 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2350. Min Range: -6.2350
Max Act: 6.2350. Min Act: -0.1700
Data Index: 1210365 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2350. Min Range: -6.2350
Max Act: 6.0163. Min Act: -0.1700
Data Index: 3552613 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2350. Min Range: -6.2350
Max Act: 5.9538. Min Act: -0.1700
Data Index: 3035331 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2350. Min Range: -6.2350
Max Act: 5.9850. Min Act: -0.1700
Data Index: 1927701 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2350. Min Range: -6.2350
Max Act: 5.9538. Min Act: -0.1700
Data Index: 5644466 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2350. Min Range: -6.2350
Max Act: 5.9538. Min Act: -0.1700
Data Index: 3801791 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2350. Min Range: -6.2350
Max Act: 5.9225. Min Act: -0.1700
Data Index: 7128045 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2350. Min Range: -6.2350
Max Act: 5.9225. Min Act: -0.1700
Data Index: 7092920 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2350. Min Range: -6.2350
Max Act: 5.9538. Min Act: -0.1700
Data Index: 6661222 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2350. Min Range: -6.2350
Max Act: 5.8600. Min Act: -0.1700
Data Index: 4952957 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2350. Min Range: -6.2350
Max Act: 5.8600. Min Act: -0.1700
Data Index: 878837 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2350. Min Range: -6.2350
Max Act: 5.7975. Min Act: -0.1700
Data Index: 6068592 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2350. Min Range: -6.2350
Max Act: 5.7975. Min Act: -0.1700
Data Index: 5487369 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2350. Min Range: -6.2350
Max Act: 5.7975. Min Act: -0.1700
Data Index: 4739274 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2350. Min Range: -6.2350
Max Act: 5.7975. Min Act: -0.1700
Data Index: 4625391 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2350. Min Range: -6.2350
Max Act: 5.7350. Min Act: -0.1700
Data Index: 7728533 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2350. Min Range: -6.2350
Max Act: 5.7975. Min Act: -0.1700
Data Index: 6480465 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2350. Min Range: -6.2350
Max Act: 5.7663. Min Act: -0.1700
Data Index: 6775204 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2350. Min Range: -6.2350
Max Act: 5.7350. Min Act: -0.1700
Data Index: 3982301 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2350. Min Range: -6.2350
Max Act: 5.7663. Min Act: -0.1700
Data Index: 5944507 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #19