Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3034 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5837. Min Range: -8.5837
Max Act: 8.5837. Min Act: -0.1700
Data Index: 4206770 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5837. Min Range: -8.5837
Max Act: 8.5212. Min Act: -0.1700
Data Index: 2709334 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5837. Min Range: -8.5837
Max Act: 8.2399. Min Act: -0.1700
Data Index: 1865799 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5837. Min Range: -8.5837
Max Act: 8.2087. Min Act: -0.1700
Data Index: 2426138 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5837. Min Range: -8.5837
Max Act: 8.2399. Min Act: -0.1700
Data Index: 7089200 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5837. Min Range: -8.5837
Max Act: 8.1462. Min Act: -0.1700
Data Index: 1180673 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5837. Min Range: -8.5837
Max Act: 8.1462. Min Act: -0.1700
Data Index: 693050 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5837. Min Range: -8.5837
Max Act: 8.1462. Min Act: -0.1700
Data Index: 5283365 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5837. Min Range: -8.5837
Max Act: 8.1149. Min Act: -0.1700
Data Index: 1957582 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5837. Min Range: -8.5837
Max Act: 8.1462. Min Act: -0.1700
Data Index: 6151420 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5837. Min Range: -8.5837
Max Act: 8.1149. Min Act: -0.1700
Data Index: 3483405 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5837. Min Range: -8.5837
Max Act: 8.0524. Min Act: -0.1700
Data Index: 1456545 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5837. Min Range: -8.5837
Max Act: 8.0524. Min Act: -0.1700
Data Index: 5172400 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5837. Min Range: -8.5837
Max Act: 8.0524. Min Act: -0.1700
Data Index: 6401265 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5837. Min Range: -8.5837
Max Act: 8.0212. Min Act: -0.1700
Data Index: 128426 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5837. Min Range: -8.5837
Max Act: 8.0212. Min Act: -0.1700
Data Index: 5396917 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5837. Min Range: -8.5837
Max Act: 8.0212. Min Act: -0.1700
Data Index: 2093801 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5837. Min Range: -8.5837
Max Act: 8.0524. Min Act: -0.1700
Data Index: 4046740 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5837. Min Range: -8.5837
Max Act: 8.0212. Min Act: -0.1700
Data Index: 1372521 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5837. Min Range: -8.5837
Max Act: 7.9899. Min Act: -0.1700
Data Index: 2607603 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #19