Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 40 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.6375. Min Range: -2.6375
Max Act: 2.6375. Min Act: -0.1700
Data Index: 155297 (C4 (Web Text))
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6375. Min Range: -2.6375
Max Act: 2.5570. Min Act: -0.1700
Data Index: 714445 (C4 (Web Text))
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6375. Min Range: -2.6375
Max Act: 2.5409. Min Act: -0.1700
Data Index: 1270880 (C4 (Web Text))
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6375. Min Range: -2.6375
Max Act: 2.5085. Min Act: -0.1700
Data Index: 137530 (C4 (Web Text))
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6375. Min Range: -2.6375
Max Act: 2.5247. Min Act: -0.1700
Data Index: 867776 (C4 (Web Text))
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6375. Min Range: -2.6375
Max Act: 2.4923. Min Act: -0.1700
Data Index: 6235 (C4 (Web Text))
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6375. Min Range: -2.6375
Max Act: 2.4761. Min Act: -0.1700
Data Index: 363447 (C4 (Web Text))
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6375. Min Range: -2.6375
Max Act: 2.4761. Min Act: -0.1700
Data Index: 589713 (C4 (Web Text))
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6375. Min Range: -2.6375
Max Act: 2.4761. Min Act: -0.1700
Data Index: 631044 (C4 (Web Text))
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6375. Min Range: -2.6375
Max Act: 2.4761. Min Act: -0.1700
Data Index: 706380 (C4 (Web Text))
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6375. Min Range: -2.6375
Max Act: 2.4761. Min Act: -0.1700
Data Index: 1118828 (C4 (Web Text))
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6375. Min Range: -2.6375
Max Act: 2.4599. Min Act: -0.1700
Data Index: 904792 (C4 (Web Text))
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6375. Min Range: -2.6375
Max Act: 2.4761. Min Act: -0.1700
Data Index: 982595 (C4 (Web Text))
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6375. Min Range: -2.6375
Max Act: 2.4599. Min Act: -0.1700
Data Index: 148220 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6375. Min Range: -2.6375
Max Act: 2.4599. Min Act: -0.1700
Data Index: 37206 (C4 (Web Text))
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6375. Min Range: -2.6375
Max Act: 2.4599. Min Act: -0.1700
Data Index: 767147 (C4 (Web Text))
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6375. Min Range: -2.6375
Max Act: 2.4436. Min Act: -0.1700
Data Index: 216181 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6375. Min Range: -2.6375
Max Act: 2.4436. Min Act: -0.1700
Data Index: 1082925 (C4 (Web Text))
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6375. Min Range: -2.6375
Max Act: 2.4436. Min Act: -0.1700
Data Index: 1086469 (C4 (Web Text))
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6375. Min Range: -2.6375
Max Act: 2.4436. Min Act: -0.1700
Data Index: 500817 (C4 (Web Text))
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #19