Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1854 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1499. Min Range: -7.1499
Max Act: 7.1499. Min Act: -0.1700
Data Index: 5002783 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1499. Min Range: -7.1499
Max Act: 6.9624. Min Act: -0.1700
Data Index: 33667 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1499. Min Range: -7.1499
Max Act: 6.8686. Min Act: -0.1700
Data Index: 7459971 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1499. Min Range: -7.1499
Max Act: 6.7124. Min Act: -0.1700
Data Index: 2841687 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1499. Min Range: -7.1499
Max Act: 6.6186. Min Act: -0.1700
Data Index: 8263582 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1499. Min Range: -7.1499
Max Act: 6.5874. Min Act: -0.1700
Data Index: 321736 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1499. Min Range: -7.1499
Max Act: 6.6186. Min Act: -0.1700
Data Index: 2295264 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1499. Min Range: -7.1499
Max Act: 6.6186. Min Act: -0.1700
Data Index: 6485631 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1499. Min Range: -7.1499
Max Act: 6.5561. Min Act: -0.1700
Data Index: 2988564 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1499. Min Range: -7.1499
Max Act: 6.4624. Min Act: -0.1700
Data Index: 822876 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1499. Min Range: -7.1499
Max Act: 6.4624. Min Act: -0.1700
Data Index: 6260414 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1499. Min Range: -7.1499
Max Act: 6.4311. Min Act: -0.1700
Data Index: 5693403 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1499. Min Range: -7.1499
Max Act: 6.3999. Min Act: -0.1700
Data Index: 7385420 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1499. Min Range: -7.1499
Max Act: 6.3999. Min Act: -0.1700
Data Index: 3649196 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1499. Min Range: -7.1499
Max Act: 6.4311. Min Act: -0.1700
Data Index: 6004418 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1499. Min Range: -7.1499
Max Act: 6.3374. Min Act: -0.1700
Data Index: 6528704 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1499. Min Range: -7.1499
Max Act: 6.3686. Min Act: -0.1700
Data Index: 6477506 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1499. Min Range: -7.1499
Max Act: 6.3374. Min Act: -0.1700
Data Index: 5008620 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1499. Min Range: -7.1499
Max Act: 6.3061. Min Act: -0.1700
Data Index: 5611530 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1499. Min Range: -7.1499
Max Act: 6.3061. Min Act: -0.1700
Data Index: 5778814 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #19