Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 218 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9595. Min Range: -4.9595
Max Act: 4.9595. Min Act: -0.1700
Data Index: 7744021 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9595. Min Range: -4.9595
Max Act: 4.7407. Min Act: -0.1700
Data Index: 1750330 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9595. Min Range: -4.9595
Max Act: 4.7407. Min Act: -0.1700
Data Index: 7497665 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9595. Min Range: -4.9595
Max Act: 4.6782. Min Act: -0.1700
Data Index: 7754870 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9595. Min Range: -4.9595
Max Act: 4.6470. Min Act: -0.1700
Data Index: 2440901 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9595. Min Range: -4.9595
Max Act: 4.6157. Min Act: -0.1700
Data Index: 5292178 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9595. Min Range: -4.9595
Max Act: 4.6157. Min Act: -0.1700
Data Index: 5780527 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9595. Min Range: -4.9595
Max Act: 4.5220. Min Act: -0.1700
Data Index: 4353313 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9595. Min Range: -4.9595
Max Act: 4.5220. Min Act: -0.1700
Data Index: 8583043 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9595. Min Range: -4.9595
Max Act: 4.4907. Min Act: -0.1700
Data Index: 3908759 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9595. Min Range: -4.9595
Max Act: 4.4907. Min Act: -0.1700
Data Index: 5782137 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9595. Min Range: -4.9595
Max Act: 4.4907. Min Act: -0.1700
Data Index: 445779 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9595. Min Range: -4.9595
Max Act: 4.4907. Min Act: -0.1700
Data Index: 214290 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9595. Min Range: -4.9595
Max Act: 4.4907. Min Act: -0.1700
Data Index: 4482517 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9595. Min Range: -4.9595
Max Act: 4.4595. Min Act: -0.1700
Data Index: 2259810 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9595. Min Range: -4.9595
Max Act: 4.4595. Min Act: -0.1700
Data Index: 3775889 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9595. Min Range: -4.9595
Max Act: 4.4595. Min Act: -0.1700
Data Index: 3316734 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9595. Min Range: -4.9595
Max Act: 4.4907. Min Act: -0.1700
Data Index: 3316664 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9595. Min Range: -4.9595
Max Act: 4.4595. Min Act: -0.1700
Data Index: 7774305 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9595. Min Range: -4.9595
Max Act: 4.4595. Min Act: -0.1700
Data Index: 1280745 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #19