Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 929 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8048. Min Range: -4.8048
Max Act: 4.8048. Min Act: -0.1700
Data Index: 5250589 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8048. Min Range: -4.8048
Max Act: 4.7735. Min Act: -0.1700
Data Index: 3141982 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8048. Min Range: -4.8048
Max Act: 4.6798. Min Act: -0.1700
Data Index: 3497283 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8048. Min Range: -4.8048
Max Act: 4.6485. Min Act: -0.1700
Data Index: 1000412 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8048. Min Range: -4.8048
Max Act: 4.5860. Min Act: -0.1700
Data Index: 4365725 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8048. Min Range: -4.8048
Max Act: 4.5860. Min Act: -0.1700
Data Index: 335300 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8048. Min Range: -4.8048
Max Act: 4.5548. Min Act: -0.1700
Data Index: 4379959 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8048. Min Range: -4.8048
Max Act: 4.5235. Min Act: -0.1700
Data Index: 833060 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8048. Min Range: -4.8048
Max Act: 4.4923. Min Act: -0.1700
Data Index: 2437980 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8048. Min Range: -4.8048
Max Act: 4.4610. Min Act: -0.1700
Data Index: 3081490 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8048. Min Range: -4.8048
Max Act: 4.4298. Min Act: -0.1700
Data Index: 4221368 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8048. Min Range: -4.8048
Max Act: 4.3673. Min Act: -0.1700
Data Index: 7180813 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8048. Min Range: -4.8048
Max Act: 4.3673. Min Act: -0.1700
Data Index: 2170467 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8048. Min Range: -4.8048
Max Act: 4.3360. Min Act: -0.1700
Data Index: 3306966 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8048. Min Range: -4.8048
Max Act: 4.3673. Min Act: -0.1700
Data Index: 4544537 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8048. Min Range: -4.8048
Max Act: 4.2735. Min Act: -0.1700
Data Index: 1837300 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8048. Min Range: -4.8048
Max Act: 4.2735. Min Act: -0.1700
Data Index: 3863754 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8048. Min Range: -4.8048
Max Act: 4.2423. Min Act: -0.1700
Data Index: 5739285 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8048. Min Range: -4.8048
Max Act: 4.2423. Min Act: -0.1700
Data Index: 813595 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8048. Min Range: -4.8048
Max Act: 4.2423. Min Act: -0.1700
Data Index: 5843676 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #19