Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2339 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5638. Min Range: -6.5638
Max Act: 6.5638. Min Act: -0.1700
Data Index: 6322881 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5638. Min Range: -6.5638
Max Act: 6.4388. Min Act: -0.1700
Data Index: 7141102 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5638. Min Range: -6.5638
Max Act: 6.4388. Min Act: -0.1700
Data Index: 6222977 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5638. Min Range: -6.5638
Max Act: 6.4388. Min Act: -0.1700
Data Index: 308601 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5638. Min Range: -6.5638
Max Act: 6.4388. Min Act: -0.1700
Data Index: 6601915 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5638. Min Range: -6.5638
Max Act: 6.4076. Min Act: -0.1700
Data Index: 2020641 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5638. Min Range: -6.5638
Max Act: 6.3763. Min Act: -0.1700
Data Index: 5007270 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5638. Min Range: -6.5638
Max Act: 6.3763. Min Act: -0.1700
Data Index: 5236611 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5638. Min Range: -6.5638
Max Act: 6.3763. Min Act: -0.1700
Data Index: 1482326 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5638. Min Range: -6.5638
Max Act: 6.3138. Min Act: -0.1700
Data Index: 526558 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5638. Min Range: -6.5638
Max Act: 6.3451. Min Act: -0.1700
Data Index: 7055229 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5638. Min Range: -6.5638
Max Act: 6.2826. Min Act: -0.1700
Data Index: 2900797 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5638. Min Range: -6.5638
Max Act: 6.3138. Min Act: -0.1699
Data Index: 3712146 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5638. Min Range: -6.5638
Max Act: 6.2513. Min Act: -0.1700
Data Index: 4419322 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5638. Min Range: -6.5638
Max Act: 6.2513. Min Act: -0.1684
Data Index: 4071906 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5638. Min Range: -6.5638
Max Act: 6.2826. Min Act: -0.1700
Data Index: 354701 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5638. Min Range: -6.5638
Max Act: 6.2513. Min Act: -0.1698
Data Index: 3886289 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5638. Min Range: -6.5638
Max Act: 6.2201. Min Act: -0.1700
Data Index: 5384150 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5638. Min Range: -6.5638
Max Act: 6.2201. Min Act: -0.1700
Data Index: 5491236 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5638. Min Range: -6.5638
Max Act: 6.2201. Min Act: -0.1696
Data Index: 7859439 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19