Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4577 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8040. Min Range: -3.8040
Max Act: 3.8040. Min Act: -0.1700
Data Index: 5569033 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8040. Min Range: -3.8040
Max Act: 3.7884. Min Act: -0.1700
Data Index: 4812515 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8040. Min Range: -3.8040
Max Act: 3.6632. Min Act: -0.1700
Data Index: 42261 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8040. Min Range: -3.8040
Max Act: 3.6319. Min Act: -0.1700
Data Index: 7835623 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8040. Min Range: -3.8040
Max Act: 3.5850. Min Act: -0.1700
Data Index: 2589350 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8040. Min Range: -3.8040
Max Act: 3.6006. Min Act: -0.1700
Data Index: 3530151 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8040. Min Range: -3.8040
Max Act: 3.5693. Min Act: -0.1700
Data Index: 2574915 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8040. Min Range: -3.8040
Max Act: 3.5693. Min Act: -0.1700
Data Index: 2940210 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8040. Min Range: -3.8040
Max Act: 3.5693. Min Act: -0.1700
Data Index: 5638516 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8040. Min Range: -3.8040
Max Act: 3.5693. Min Act: -0.1700
Data Index: 4385353 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8040. Min Range: -3.8040
Max Act: 3.5537. Min Act: -0.1700
Data Index: 4482475 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8040. Min Range: -3.8040
Max Act: 3.5380. Min Act: -0.1700
Data Index: 2609284 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8040. Min Range: -3.8040
Max Act: 3.5380. Min Act: -0.1700
Data Index: 1204134 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8040. Min Range: -3.8040
Max Act: 3.5224. Min Act: -0.1700
Data Index: 8031669 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8040. Min Range: -3.8040
Max Act: 3.5224. Min Act: -0.1700
Data Index: 4435073 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8040. Min Range: -3.8040
Max Act: 3.4597. Min Act: -0.1700
Data Index: 6008928 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8040. Min Range: -3.8040
Max Act: 3.4754. Min Act: -0.1700
Data Index: 2798457 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8040. Min Range: -3.8040
Max Act: 3.4597. Min Act: -0.1700
Data Index: 5158331 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8040. Min Range: -3.8040
Max Act: 3.4597. Min Act: -0.1700
Data Index: 5373498 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8040. Min Range: -3.8040
Max Act: 3.4440. Min Act: -0.1700
Data Index: 6141919 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #19