Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3019 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4090. Min Range: -5.4090
Max Act: 5.4090. Min Act: -0.1700
Data Index: 7476801 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4090. Min Range: -5.4090
Max Act: 5.3465. Min Act: -0.1700
Data Index: 6282411 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4090. Min Range: -5.4090
Max Act: 5.3153. Min Act: -0.1700
Data Index: 3329970 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4090. Min Range: -5.4090
Max Act: 5.2840. Min Act: -0.1700
Data Index: 7040386 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4090. Min Range: -5.4090
Max Act: 5.2528. Min Act: -0.1700
Data Index: 5917308 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4090. Min Range: -5.4090
Max Act: 5.2840. Min Act: -0.1700
Data Index: 6271977 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4090. Min Range: -5.4090
Max Act: 5.1903. Min Act: -0.1700
Data Index: 4806491 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4090. Min Range: -5.4090
Max Act: 5.1903. Min Act: -0.1700
Data Index: 7177721 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4090. Min Range: -5.4090
Max Act: 5.1590. Min Act: -0.1700
Data Index: 1318160 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4090. Min Range: -5.4090
Max Act: 5.1278. Min Act: -0.1700
Data Index: 3307175 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4090. Min Range: -5.4090
Max Act: 5.1278. Min Act: -0.1700
Data Index: 5314947 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4090. Min Range: -5.4090
Max Act: 5.0965. Min Act: -0.1700
Data Index: 5938274 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4090. Min Range: -5.4090
Max Act: 5.1278. Min Act: -0.1700
Data Index: 2104513 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4090. Min Range: -5.4090
Max Act: 5.1278. Min Act: -0.1700
Data Index: 4339296 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4090. Min Range: -5.4090
Max Act: 5.1278. Min Act: -0.1700
Data Index: 143470 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4090. Min Range: -5.4090
Max Act: 5.1278. Min Act: -0.1700
Data Index: 3126628 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4090. Min Range: -5.4090
Max Act: 5.1278. Min Act: -0.1700
Data Index: 2343014 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4090. Min Range: -5.4090
Max Act: 5.1278. Min Act: -0.1700
Data Index: 4907131 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4090. Min Range: -5.4090
Max Act: 5.1278. Min Act: -0.1700
Data Index: 5084373 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4090. Min Range: -5.4090
Max Act: 5.0653. Min Act: -0.1700
Data Index: 4135552 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #19