Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3269 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6002. Min Range: -7.6002
Max Act: 7.6002. Min Act: -0.1700
Data Index: 251583 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6002. Min Range: -7.6002
Max Act: 6.8502. Min Act: -0.1700
Data Index: 6112624 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6002. Min Range: -7.6002
Max Act: 6.8189. Min Act: -0.1700
Data Index: 7572018 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6002. Min Range: -7.6002
Max Act: 6.8189. Min Act: -0.1700
Data Index: 5709991 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6002. Min Range: -7.6002
Max Act: 6.7564. Min Act: -0.1700
Data Index: 4504052 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6002. Min Range: -7.6002
Max Act: 6.7252. Min Act: -0.1700
Data Index: 8090094 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6002. Min Range: -7.6002
Max Act: 6.6939. Min Act: -0.1700
Data Index: 4905423 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6002. Min Range: -7.6002
Max Act: 6.6314. Min Act: -0.1700
Data Index: 3711890 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6002. Min Range: -7.6002
Max Act: 6.6314. Min Act: -0.1700
Data Index: 5945686 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6002. Min Range: -7.6002
Max Act: 6.6314. Min Act: -0.1700
Data Index: 8574202 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6002. Min Range: -7.6002
Max Act: 6.6314. Min Act: -0.1700
Data Index: 8778061 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6002. Min Range: -7.6002
Max Act: 6.6002. Min Act: -0.1700
Data Index: 456134 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6002. Min Range: -7.6002
Max Act: 6.6002. Min Act: -0.1700
Data Index: 7980496 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6002. Min Range: -7.6002
Max Act: 6.6002. Min Act: -0.1700
Data Index: 8236298 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6002. Min Range: -7.6002
Max Act: 6.5689. Min Act: -0.1700
Data Index: 4012818 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6002. Min Range: -7.6002
Max Act: 6.5689. Min Act: -0.1700
Data Index: 6512829 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6002. Min Range: -7.6002
Max Act: 6.5689. Min Act: -0.1700
Data Index: 3422269 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6002. Min Range: -7.6002
Max Act: 6.5689. Min Act: -0.1700
Data Index: 3278826 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6002. Min Range: -7.6002
Max Act: 6.5689. Min Act: -0.1700
Data Index: 7754222 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6002. Min Range: -7.6002
Max Act: 6.5377. Min Act: -0.1700
Data Index: 2525378 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #19