Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 260 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.9227. Min Range: -2.9227
Max Act: 2.9227. Min Act: -0.1700
Data Index: 810978 (C4 (Web Text))
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9227. Min Range: -2.9227
Max Act: 2.8910. Min Act: -0.1700
Data Index: 966650 (C4 (Web Text))
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9227. Min Range: -2.9227
Max Act: 2.8116. Min Act: -0.1700
Data Index: 1630125 (Python Code)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9227. Min Range: -2.9227
Max Act: 2.7956. Min Act: -0.1700
Data Index: 1353277 (C4 (Web Text))
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9227. Min Range: -2.9227
Max Act: 2.7478. Min Act: -0.1700
Data Index: 931283 (C4 (Web Text))
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9227. Min Range: -2.9227
Max Act: 2.7318. Min Act: -0.1700
Data Index: 806383 (C4 (Web Text))
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9227. Min Range: -2.9227
Max Act: 2.7318. Min Act: -0.1700
Data Index: 736802 (C4 (Web Text))
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9227. Min Range: -2.9227
Max Act: 2.7318. Min Act: -0.1700
Data Index: 28704 (C4 (Web Text))
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9227. Min Range: -2.9227
Max Act: 2.7158. Min Act: -0.1700
Data Index: 1096320 (C4 (Web Text))
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9227. Min Range: -2.9227
Max Act: 2.7158. Min Act: -0.1700
Data Index: 265384 (C4 (Web Text))
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9227. Min Range: -2.9227
Max Act: 2.6838. Min Act: -0.1700
Data Index: 728720 (C4 (Web Text))
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9227. Min Range: -2.9227
Max Act: 2.6998. Min Act: -0.1700
Data Index: 572094 (C4 (Web Text))
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9227. Min Range: -2.9227
Max Act: 2.6678. Min Act: -0.1700
Data Index: 682258 (C4 (Web Text))
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9227. Min Range: -2.9227
Max Act: 2.6678. Min Act: -0.1700
Data Index: 1158492 (C4 (Web Text))
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9227. Min Range: -2.9227
Max Act: 2.6838. Min Act: -0.1700
Data Index: 1045571 (C4 (Web Text))
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9227. Min Range: -2.9227
Max Act: 2.6838. Min Act: -0.1700
Data Index: 210371 (C4 (Web Text))
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9227. Min Range: -2.9227
Max Act: 2.6678. Min Act: -0.1700
Data Index: 321526 (C4 (Web Text))
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9227. Min Range: -2.9227
Max Act: 2.6678. Min Act: -0.1700
Data Index: 48238 (C4 (Web Text))
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9227. Min Range: -2.9227
Max Act: 2.6678. Min Act: -0.1700
Data Index: 171247 (C4 (Web Text))
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9227. Min Range: -2.9227
Max Act: 2.6678. Min Act: -0.1700
Data Index: 1269794 (C4 (Web Text))
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #19