Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1991 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.0181. Min Range: -2.0181
Max Act: 2.0181. Min Act: -0.1700
Data Index: 1456443 (Python Code)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0181. Min Range: -2.0181
Max Act: 2.0012. Min Act: -0.1700
Data Index: 1637142 (Python Code)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0181. Min Range: -2.0181
Max Act: 2.0012. Min Act: -0.1700
Data Index: 1490362 (Python Code)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0181. Min Range: -2.0181
Max Act: 1.9843. Min Act: -0.1700
Data Index: 464358 (C4 (Web Text))
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0181. Min Range: -2.0181
Max Act: 2.0012. Min Act: -0.1700
Data Index: 1509722 (Python Code)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0181. Min Range: -2.0181
Max Act: 1.9843. Min Act: -0.1700
Data Index: 1402280 (Python Code)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0181. Min Range: -2.0181
Max Act: 1.9674. Min Act: -0.1700
Data Index: 1530434 (Python Code)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0181. Min Range: -2.0181
Max Act: 1.9674. Min Act: -0.1700
Data Index: 1478930 (Python Code)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0181. Min Range: -2.0181
Max Act: 1.9505. Min Act: -0.1700
Data Index: 1473002 (Python Code)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0181. Min Range: -2.0181
Max Act: 1.9165. Min Act: -0.1700
Data Index: 1477864 (Python Code)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0181. Min Range: -2.0181
Max Act: 1.9335. Min Act: -0.1700
Data Index: 1584799 (Python Code)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0181. Min Range: -2.0181
Max Act: 1.9335. Min Act: -0.1700
Data Index: 1518893 (Python Code)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0181. Min Range: -2.0181
Max Act: 1.9165. Min Act: -0.1700
Data Index: 1461082 (Python Code)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0181. Min Range: -2.0181
Max Act: 1.9165. Min Act: -0.1700
Data Index: 1406719 (Python Code)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0181. Min Range: -2.0181
Max Act: 1.9165. Min Act: -0.1700
Data Index: 1385124 (Python Code)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0181. Min Range: -2.0181
Max Act: 1.9165. Min Act: -0.1700
Data Index: 1437340 (Python Code)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0181. Min Range: -2.0181
Max Act: 1.9165. Min Act: -0.1700
Data Index: 1643834 (Python Code)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0181. Min Range: -2.0181
Max Act: 1.9165. Min Act: -0.1700
Data Index: 357843 (C4 (Web Text))
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0181. Min Range: -2.0181
Max Act: 1.9165. Min Act: -0.1700
Data Index: 246016 (C4 (Web Text))
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0181. Min Range: -2.0181
Max Act: 1.9165. Min Act: -0.1700
Data Index: 459624 (C4 (Web Text))
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #19