Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1168 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.1036. Min Range: -2.1036
Max Act: 2.1036. Min Act: -0.1700
Data Index: 180854 (C4 (Web Text))
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1036. Min Range: -2.1036
Max Act: 2.0869. Min Act: -0.1700
Data Index: 588272 (C4 (Web Text))
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1036. Min Range: -2.1036
Max Act: 2.0365. Min Act: -0.1700
Data Index: 1234268 (C4 (Web Text))
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1036. Min Range: -2.1036
Max Act: 2.0533. Min Act: -0.1700
Data Index: 389187 (C4 (Web Text))
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1036. Min Range: -2.1036
Max Act: 2.0197. Min Act: -0.1700
Data Index: 465932 (C4 (Web Text))
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1036. Min Range: -2.1036
Max Act: 2.0028. Min Act: -0.1700
Data Index: 54116 (C4 (Web Text))
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1036. Min Range: -2.1036
Max Act: 2.0028. Min Act: -0.1700
Data Index: 203297 (C4 (Web Text))
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1036. Min Range: -2.1036
Max Act: 2.0028. Min Act: -0.1700
Data Index: 1084564 (C4 (Web Text))
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1036. Min Range: -2.1036
Max Act: 1.9859. Min Act: -0.1700
Data Index: 492409 (C4 (Web Text))
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1036. Min Range: -2.1036
Max Act: 1.9690. Min Act: -0.1700
Data Index: 868451 (C4 (Web Text))
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1036. Min Range: -2.1036
Max Act: 1.9690. Min Act: -0.1700
Data Index: 629254 (C4 (Web Text))
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1036. Min Range: -2.1036
Max Act: 1.9690. Min Act: -0.1700
Data Index: 760997 (C4 (Web Text))
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1036. Min Range: -2.1036
Max Act: 1.9690. Min Act: -0.1700
Data Index: 828508 (C4 (Web Text))
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1036. Min Range: -2.1036
Max Act: 1.9520. Min Act: -0.1700
Data Index: 140664 (C4 (Web Text))
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1036. Min Range: -2.1036
Max Act: 1.9690. Min Act: -0.1700
Data Index: 708686 (C4 (Web Text))
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1036. Min Range: -2.1036
Max Act: 1.9520. Min Act: -0.1700
Data Index: 473745 (C4 (Web Text))
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1036. Min Range: -2.1036
Max Act: 1.9520. Min Act: -0.1700
Data Index: 400517 (C4 (Web Text))
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1036. Min Range: -2.1036
Max Act: 1.9351. Min Act: -0.1700
Data Index: 1191289 (C4 (Web Text))
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1036. Min Range: -2.1036
Max Act: 1.9351. Min Act: -0.1700
Data Index: 29962 (C4 (Web Text))
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1036. Min Range: -2.1036
Max Act: 1.9351. Min Act: -0.1700
Data Index: 1171510 (C4 (Web Text))
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #19