Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 142 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.4128. Min Act: -0.1700
Data Index: 898046 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.4128. Min Act: -0.1700
Data Index: 2504300 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.3190. Min Act: -0.1700
Data Index: 48901 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.2878. Min Act: -0.1700
Data Index: 3269733 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.2565. Min Act: -0.1700
Data Index: 224240 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.2565. Min Act: -0.1700
Data Index: 1562879 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.2565. Min Act: -0.1700
Data Index: 5270431 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.2253. Min Act: -0.1700
Data Index: 598333 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.2253. Min Act: -0.1700
Data Index: 1206350 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.1628. Min Act: -0.1700
Data Index: 5063269 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.1628. Min Act: -0.1700
Data Index: 7215221 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.1628. Min Act: -0.1700
Data Index: 4531359 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.1315. Min Act: -0.1700
Data Index: 3062901 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.1315. Min Act: -0.1700
Data Index: 8169038 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.1315. Min Act: -0.1700
Data Index: 3909702 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.1315. Min Act: -0.1700
Data Index: 2869108 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.1315. Min Act: -0.1700
Data Index: 6130830 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.1003. Min Act: -0.1700
Data Index: 1831321 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.1003. Min Act: -0.1700
Data Index: 7656083 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.1003. Min Act: -0.1700
Data Index: 6639794 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #19