Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5620 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1101. Min Range: -8.1101
Max Act: 8.1101. Min Act: -0.1700
Data Index: 4750069 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1101. Min Range: -8.1101
Max Act: 7.7351. Min Act: -0.1700
Data Index: 597322 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1101. Min Range: -8.1101
Max Act: 7.6726. Min Act: -0.1700
Data Index: 3125429 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1101. Min Range: -8.1101
Max Act: 7.6101. Min Act: -0.1700
Data Index: 485142 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1101. Min Range: -8.1101
Max Act: 7.6726. Min Act: -0.1700
Data Index: 1727290 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1101. Min Range: -8.1101
Max Act: 7.4226. Min Act: -0.1700
Data Index: 783271 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1101. Min Range: -8.1101
Max Act: 7.3913. Min Act: -0.1700
Data Index: 6850602 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1101. Min Range: -8.1101
Max Act: 7.3288. Min Act: -0.1700
Data Index: 4440088 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1101. Min Range: -8.1101
Max Act: 7.1101. Min Act: -0.1700
Data Index: 6781329 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1101. Min Range: -8.1101
Max Act: 7.1101. Min Act: -0.1700
Data Index: 8325413 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1101. Min Range: -8.1101
Max Act: 7.0788. Min Act: -0.1700
Data Index: 5992445 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1101. Min Range: -8.1101
Max Act: 7.0788. Min Act: -0.1700
Data Index: 1039693 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1101. Min Range: -8.1101
Max Act: 7.0163. Min Act: -0.1700
Data Index: 4697787 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1101. Min Range: -8.1101
Max Act: 7.0476. Min Act: -0.1700
Data Index: 2220776 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1101. Min Range: -8.1101
Max Act: 6.9851. Min Act: -0.1700
Data Index: 2154895 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1101. Min Range: -8.1101
Max Act: 6.9851. Min Act: -0.1700
Data Index: 7887362 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1101. Min Range: -8.1101
Max Act: 6.9538. Min Act: -0.1700
Data Index: 1741946 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1101. Min Range: -8.1101
Max Act: 6.9538. Min Act: -0.1700
Data Index: 3014797 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1101. Min Range: -8.1101
Max Act: 6.9538. Min Act: -0.1700
Data Index: 5131377 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1101. Min Range: -8.1101
Max Act: 6.9538. Min Act: -0.1700
Data Index: 1310014 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #19