Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 705 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.5097. Min Range: -2.5097
Max Act: 2.5097. Min Act: -0.1700
Data Index: 1295939 (C4 (Web Text))
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5097. Min Range: -2.5097
Max Act: 2.5097. Min Act: -0.1700
Data Index: 1545776 (Python Code)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5097. Min Range: -2.5097
Max Act: 2.5097. Min Act: -0.1700
Data Index: 1420256 (Python Code)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5097. Min Range: -2.5097
Max Act: 2.4773. Min Act: -0.1700
Data Index: 189840 (C4 (Web Text))
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5097. Min Range: -2.5097
Max Act: 2.4610. Min Act: -0.1700
Data Index: 64218 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5097. Min Range: -2.5097
Max Act: 2.4773. Min Act: -0.1700
Data Index: 935849 (C4 (Web Text))
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5097. Min Range: -2.5097
Max Act: 2.4448. Min Act: -0.1700
Data Index: 554157 (C4 (Web Text))
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5097. Min Range: -2.5097
Max Act: 2.4610. Min Act: -0.1700
Data Index: 1308268 (C4 (Web Text))
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5097. Min Range: -2.5097
Max Act: 2.4122. Min Act: -0.1700
Data Index: 1406919 (Python Code)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5097. Min Range: -2.5097
Max Act: 2.4285. Min Act: -0.1700
Data Index: 1252169 (C4 (Web Text))
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5097. Min Range: -2.5097
Max Act: 2.4122. Min Act: -0.1700
Data Index: 205679 (C4 (Web Text))
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5097. Min Range: -2.5097
Max Act: 2.4285. Min Act: -0.1700
Data Index: 1098853 (C4 (Web Text))
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5097. Min Range: -2.5097
Max Act: 2.4122. Min Act: -0.1700
Data Index: 214316 (C4 (Web Text))
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5097. Min Range: -2.5097
Max Act: 2.4122. Min Act: -0.1700
Data Index: 369478 (C4 (Web Text))
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5097. Min Range: -2.5097
Max Act: 2.4122. Min Act: -0.1700
Data Index: 718494 (C4 (Web Text))
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5097. Min Range: -2.5097
Max Act: 2.4122. Min Act: -0.1699
Data Index: 1394269 (Python Code)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5097. Min Range: -2.5097
Max Act: 2.4122. Min Act: -0.1700
Data Index: 56880 (C4 (Web Text))
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5097. Min Range: -2.5097
Max Act: 2.3959. Min Act: -0.1700
Data Index: 758823 (C4 (Web Text))
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5097. Min Range: -2.5097
Max Act: 2.3959. Min Act: -0.1700
Data Index: 1432357 (Python Code)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5097. Min Range: -2.5097
Max Act: 2.3796. Min Act: -0.1700
Data Index: 1427078 (Python Code)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #19