Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1746 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4793. Min Range: -4.4793
Max Act: 4.4793. Min Act: -0.1700
Data Index: 481888 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4793. Min Range: -4.4793
Max Act: 4.4793. Min Act: -0.1700
Data Index: 4291823 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4793. Min Range: -4.4793
Max Act: 4.4793. Min Act: -0.1700
Data Index: 3003768 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4793. Min Range: -4.4793
Max Act: 4.4481. Min Act: -0.1700
Data Index: 2538891 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4793. Min Range: -4.4793
Max Act: 4.3856. Min Act: -0.1700
Data Index: 8345323 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4793. Min Range: -4.4793
Max Act: 4.4168. Min Act: -0.1700
Data Index: 7048915 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4793. Min Range: -4.4793
Max Act: 4.3231. Min Act: -0.1700
Data Index: 7616103 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4793. Min Range: -4.4793
Max Act: 4.3231. Min Act: -0.1700
Data Index: 8004173 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4793. Min Range: -4.4793
Max Act: 4.3231. Min Act: -0.1700
Data Index: 1915485 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4793. Min Range: -4.4793
Max Act: 4.2918. Min Act: -0.1700
Data Index: 5839974 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4793. Min Range: -4.4793
Max Act: 4.2918. Min Act: -0.1700
Data Index: 2414259 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4793. Min Range: -4.4793
Max Act: 4.2293. Min Act: -0.1700
Data Index: 5591648 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4793. Min Range: -4.4793
Max Act: 4.2293. Min Act: -0.1700
Data Index: 2991028 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4793. Min Range: -4.4793
Max Act: 4.2606. Min Act: -0.1700
Data Index: 6389868 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4793. Min Range: -4.4793
Max Act: 4.2606. Min Act: -0.1700
Data Index: 608968 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4793. Min Range: -4.4793
Max Act: 4.2606. Min Act: -0.1700
Data Index: 6530358 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4793. Min Range: -4.4793
Max Act: 4.2606. Min Act: -0.1700
Data Index: 687163 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4793. Min Range: -4.4793
Max Act: 4.2606. Min Act: -0.1700
Data Index: 4469962 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4793. Min Range: -4.4793
Max Act: 4.2606. Min Act: -0.1700
Data Index: 4381716 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4793. Min Range: -4.4793
Max Act: 4.2606. Min Act: -0.1700
Data Index: 3182576 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #19