Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3200 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9772. Min Range: -4.9772
Max Act: 4.9772. Min Act: -0.1700
Data Index: 4037094 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9772. Min Range: -4.9772
Max Act: 4.9772. Min Act: -0.1700
Data Index: 1971792 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9772. Min Range: -4.9772
Max Act: 4.9460. Min Act: -0.1700
Data Index: 5474753 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9772. Min Range: -4.9772
Max Act: 4.9147. Min Act: -0.1700
Data Index: 4675979 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9772. Min Range: -4.9772
Max Act: 4.8835. Min Act: -0.1700
Data Index: 6959667 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9772. Min Range: -4.9772
Max Act: 4.8210. Min Act: -0.1700
Data Index: 1592831 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9772. Min Range: -4.9772
Max Act: 4.8210. Min Act: -0.1700
Data Index: 4865413 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9772. Min Range: -4.9772
Max Act: 4.8210. Min Act: -0.1700
Data Index: 7661579 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9772. Min Range: -4.9772
Max Act: 4.8210. Min Act: -0.1700
Data Index: 8114344 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9772. Min Range: -4.9772
Max Act: 4.7585. Min Act: -0.1700
Data Index: 4300949 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9772. Min Range: -4.9772
Max Act: 4.7897. Min Act: -0.1700
Data Index: 2830270 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9772. Min Range: -4.9772
Max Act: 4.7897. Min Act: -0.1700
Data Index: 990466 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9772. Min Range: -4.9772
Max Act: 4.7585. Min Act: -0.1700
Data Index: 2780764 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9772. Min Range: -4.9772
Max Act: 4.8210. Min Act: -0.1700
Data Index: 3307108 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9772. Min Range: -4.9772
Max Act: 4.7897. Min Act: -0.1700
Data Index: 3256736 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9772. Min Range: -4.9772
Max Act: 4.7897. Min Act: -0.1700
Data Index: 6457827 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9772. Min Range: -4.9772
Max Act: 4.7272. Min Act: -0.1700
Data Index: 1814374 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9772. Min Range: -4.9772
Max Act: 4.7897. Min Act: -0.1700
Data Index: 6051374 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9772. Min Range: -4.9772
Max Act: 4.7897. Min Act: -0.1700
Data Index: 2082659 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9772. Min Range: -4.9772
Max Act: 4.7585. Min Act: -0.1700
Data Index: 7895023 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #19