Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1989 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.3890. Min Range: -2.3890
Max Act: 2.3890. Min Act: -0.1700
Data Index: 306898 (C4 (Web Text))
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3890. Min Range: -2.3890
Max Act: 2.3563. Min Act: -0.1700
Data Index: 350425 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3890. Min Range: -2.3890
Max Act: 2.3727. Min Act: -0.1700
Data Index: 1366204 (Python Code)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3890. Min Range: -2.3890
Max Act: 2.3563. Min Act: -0.1700
Data Index: 1122779 (C4 (Web Text))
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3890. Min Range: -2.3890
Max Act: 2.3727. Min Act: -0.1700
Data Index: 786524 (C4 (Web Text))
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3890. Min Range: -2.3890
Max Act: 2.3399. Min Act: -0.1700
Data Index: 351166 (C4 (Web Text))
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3890. Min Range: -2.3890
Max Act: 2.3235. Min Act: -0.1700
Data Index: 1639913 (Python Code)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3890. Min Range: -2.3890
Max Act: 2.3235. Min Act: -0.1700
Data Index: 1526700 (Python Code)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3890. Min Range: -2.3890
Max Act: 2.3235. Min Act: -0.1700
Data Index: 647290 (C4 (Web Text))
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3890. Min Range: -2.3890
Max Act: 2.3235. Min Act: -0.1700
Data Index: 1080870 (C4 (Web Text))
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3890. Min Range: -2.3890
Max Act: 2.3235. Min Act: -0.1700
Data Index: 334219 (C4 (Web Text))
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3890. Min Range: -2.3890
Max Act: 2.3235. Min Act: -0.1700
Data Index: 846258 (C4 (Web Text))
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3890. Min Range: -2.3890
Max Act: 2.3071. Min Act: -0.1700
Data Index: 1036541 (C4 (Web Text))
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3890. Min Range: -2.3890
Max Act: 2.3071. Min Act: -0.1700
Data Index: 1065804 (C4 (Web Text))
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3890. Min Range: -2.3890
Max Act: 2.2907. Min Act: -0.1700
Data Index: 274699 (C4 (Web Text))
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3890. Min Range: -2.3890
Max Act: 2.3071. Min Act: -0.1700
Data Index: 1099537 (C4 (Web Text))
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3890. Min Range: -2.3890
Max Act: 2.3071. Min Act: -0.1700
Data Index: 1006197 (C4 (Web Text))
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3890. Min Range: -2.3890
Max Act: 2.3071. Min Act: -0.1700
Data Index: 791290 (C4 (Web Text))
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3890. Min Range: -2.3890
Max Act: 2.3071. Min Act: -0.1700
Data Index: 720917 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3890. Min Range: -2.3890
Max Act: 2.3071. Min Act: -0.1700
Data Index: 1014649 (C4 (Web Text))
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #19