Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 861 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.6459. Min Range: -4.6459
Max Act: 4.6459. Min Act: -0.1700
Data Index: 1166767 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6459. Min Range: -4.6459
Max Act: 4.6146. Min Act: -0.1700
Data Index: 458620 (C4 (Web Text))
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6459. Min Range: -4.6459
Max Act: 4.5521. Min Act: -0.1700
Data Index: 189252 (C4 (Web Text))
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6459. Min Range: -4.6459
Max Act: 4.5521. Min Act: -0.1700
Data Index: 768339 (C4 (Web Text))
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6459. Min Range: -4.6459
Max Act: 4.5521. Min Act: -0.1700
Data Index: 436407 (C4 (Web Text))
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6459. Min Range: -4.6459
Max Act: 4.5521. Min Act: -0.1700
Data Index: 383702 (C4 (Web Text))
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6459. Min Range: -4.6459
Max Act: 4.5521. Min Act: -0.1700
Data Index: 36543 (C4 (Web Text))
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6459. Min Range: -4.6459
Max Act: 4.4896. Min Act: -0.1700
Data Index: 651047 (C4 (Web Text))
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6459. Min Range: -4.6459
Max Act: 4.5209. Min Act: -0.1700
Data Index: 81417 (C4 (Web Text))
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6459. Min Range: -4.6459
Max Act: 4.5209. Min Act: -0.1700
Data Index: 1332198 (C4 (Web Text))
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6459. Min Range: -4.6459
Max Act: 4.4584. Min Act: -0.1700
Data Index: 1213824 (C4 (Web Text))
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6459. Min Range: -4.6459
Max Act: 4.4584. Min Act: -0.1700
Data Index: 220523 (C4 (Web Text))
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6459. Min Range: -4.6459
Max Act: 4.4584. Min Act: -0.1700
Data Index: 847071 (C4 (Web Text))
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6459. Min Range: -4.6459
Max Act: 4.4584. Min Act: -0.1700
Data Index: 444446 (C4 (Web Text))
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6459. Min Range: -4.6459
Max Act: 4.4896. Min Act: -0.1700
Data Index: 363652 (C4 (Web Text))
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6459. Min Range: -4.6459
Max Act: 4.4584. Min Act: -0.1700
Data Index: 1241067 (C4 (Web Text))
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6459. Min Range: -4.6459
Max Act: 4.3959. Min Act: -0.1700
Data Index: 70782 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6459. Min Range: -4.6459
Max Act: 4.4271. Min Act: -0.1700
Data Index: 198938 (C4 (Web Text))
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6459. Min Range: -4.6459
Max Act: 4.4271. Min Act: -0.1700
Data Index: 1146570 (C4 (Web Text))
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6459. Min Range: -4.6459
Max Act: 4.4271. Min Act: -0.1700
Data Index: 810982 (C4 (Web Text))
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #19