Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1452 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.5377. Min Range: -2.5377
Max Act: 2.5377. Min Act: -0.1700
Data Index: 1524413 (Python Code)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5377. Min Range: -2.5377
Max Act: 2.5377. Min Act: -0.1700
Data Index: 201906 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5377. Min Range: -2.5377
Max Act: 2.5377. Min Act: -0.1700
Data Index: 1387636 (Python Code)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5377. Min Range: -2.5377
Max Act: 2.5377. Min Act: -0.1700
Data Index: 1006140 (C4 (Web Text))
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5377. Min Range: -2.5377
Max Act: 2.5377. Min Act: -0.1700
Data Index: 225368 (C4 (Web Text))
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5377. Min Range: -2.5377
Max Act: 2.5215. Min Act: -0.1700
Data Index: 1175389 (C4 (Web Text))
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5377. Min Range: -2.5377
Max Act: 2.5377. Min Act: -0.1700
Data Index: 1576889 (Python Code)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5377. Min Range: -2.5377
Max Act: 2.5053. Min Act: -0.1700
Data Index: 409795 (C4 (Web Text))
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5377. Min Range: -2.5377
Max Act: 2.5215. Min Act: -0.1700
Data Index: 803760 (C4 (Web Text))
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5377. Min Range: -2.5377
Max Act: 2.5215. Min Act: -0.1700
Data Index: 371924 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5377. Min Range: -2.5377
Max Act: 2.5053. Min Act: -0.1700
Data Index: 1029289 (C4 (Web Text))
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5377. Min Range: -2.5377
Max Act: 2.5053. Min Act: -0.1700
Data Index: 530361 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5377. Min Range: -2.5377
Max Act: 2.4891. Min Act: -0.1700
Data Index: 277570 (C4 (Web Text))
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5377. Min Range: -2.5377
Max Act: 2.4891. Min Act: -0.1700
Data Index: 1155978 (C4 (Web Text))
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5377. Min Range: -2.5377
Max Act: 2.4891. Min Act: -0.1700
Data Index: 1428232 (Python Code)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5377. Min Range: -2.5377
Max Act: 2.4729. Min Act: -0.1700
Data Index: 1372381 (Python Code)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5377. Min Range: -2.5377
Max Act: 2.4891. Min Act: -0.1700
Data Index: 1598711 (Python Code)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5377. Min Range: -2.5377
Max Act: 2.4891. Min Act: -0.1700
Data Index: 1444359 (Python Code)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5377. Min Range: -2.5377
Max Act: 2.4729. Min Act: -0.1700
Data Index: 969253 (C4 (Web Text))
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5377. Min Range: -2.5377
Max Act: 2.4891. Min Act: -0.1700
Data Index: 58213 (C4 (Web Text))
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #19