Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 490 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2416. Min Range: -5.2416
Max Act: 5.2416. Min Act: -0.1700
Data Index: 7073537 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2416. Min Range: -5.2416
Max Act: 4.9916. Min Act: -0.1700
Data Index: 6125769 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2416. Min Range: -5.2416
Max Act: 4.9604. Min Act: -0.1700
Data Index: 229162 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2416. Min Range: -5.2416
Max Act: 4.9916. Min Act: -0.1700
Data Index: 2115598 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2416. Min Range: -5.2416
Max Act: 4.9291. Min Act: -0.1700
Data Index: 2359888 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2416. Min Range: -5.2416
Max Act: 4.9291. Min Act: -0.1700
Data Index: 4967998 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2416. Min Range: -5.2416
Max Act: 4.8666. Min Act: -0.1700
Data Index: 6969137 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2416. Min Range: -5.2416
Max Act: 4.8979. Min Act: -0.1700
Data Index: 2062499 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2416. Min Range: -5.2416
Max Act: 4.8666. Min Act: -0.1700
Data Index: 6923973 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2416. Min Range: -5.2416
Max Act: 4.8354. Min Act: -0.1700
Data Index: 2182336 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2416. Min Range: -5.2416
Max Act: 4.8041. Min Act: -0.1700
Data Index: 3862893 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2416. Min Range: -5.2416
Max Act: 4.7416. Min Act: -0.1700
Data Index: 3684407 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2416. Min Range: -5.2416
Max Act: 4.7729. Min Act: -0.1700
Data Index: 4488131 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2416. Min Range: -5.2416
Max Act: 4.7729. Min Act: -0.1700
Data Index: 6047225 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2416. Min Range: -5.2416
Max Act: 4.7416. Min Act: -0.1700
Data Index: 6944423 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2416. Min Range: -5.2416
Max Act: 4.7104. Min Act: -0.1700
Data Index: 481937 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2416. Min Range: -5.2416
Max Act: 4.7416. Min Act: -0.1700
Data Index: 5612700 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2416. Min Range: -5.2416
Max Act: 4.7416. Min Act: -0.1700
Data Index: 6934047 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2416. Min Range: -5.2416
Max Act: 4.6791. Min Act: -0.1700
Data Index: 4373142 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2416. Min Range: -5.2416
Max Act: 4.7104. Min Act: -0.1700
Data Index: 83759 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #19