Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1870 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.0512. Min Range: -2.0512
Max Act: 2.0512. Min Act: -0.1700
Data Index: 1085399 (C4 (Web Text))
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0512. Min Range: -2.0512
Max Act: 1.9838. Min Act: -0.1700
Data Index: 93268 (C4 (Web Text))
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0512. Min Range: -2.0512
Max Act: 1.9499. Min Act: -0.1700
Data Index: 397873 (C4 (Web Text))
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0512. Min Range: -2.0512
Max Act: 1.9499. Min Act: -0.1700
Data Index: 744518 (C4 (Web Text))
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0512. Min Range: -2.0512
Max Act: 1.9414. Min Act: -0.1700
Data Index: 1178205 (C4 (Web Text))
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0512. Min Range: -2.0512
Max Act: 1.9244. Min Act: -0.1700
Data Index: 936821 (C4 (Web Text))
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0512. Min Range: -2.0512
Max Act: 1.9159. Min Act: -0.1700
Data Index: 389765 (C4 (Web Text))
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0512. Min Range: -2.0512
Max Act: 1.9074. Min Act: -0.1700
Data Index: 529076 (C4 (Web Text))
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0512. Min Range: -2.0512
Max Act: 1.9074. Min Act: -0.1700
Data Index: 1255471 (C4 (Web Text))
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0512. Min Range: -2.0512
Max Act: 1.8903. Min Act: -0.1700
Data Index: 356244 (C4 (Web Text))
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0512. Min Range: -2.0512
Max Act: 1.8903. Min Act: -0.1700
Data Index: 702693 (C4 (Web Text))
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0512. Min Range: -2.0512
Max Act: 1.8733. Min Act: -0.1700
Data Index: 561886 (C4 (Web Text))
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0512. Min Range: -2.0512
Max Act: 1.8818. Min Act: -0.1700
Data Index: 589915 (C4 (Web Text))
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0512. Min Range: -2.0512
Max Act: 1.8818. Min Act: -0.1700
Data Index: 127021 (C4 (Web Text))
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0512. Min Range: -2.0512
Max Act: 1.8733. Min Act: -0.1700
Data Index: 985987 (C4 (Web Text))
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0512. Min Range: -2.0512
Max Act: 1.8818. Min Act: -0.1700
Data Index: 537980 (C4 (Web Text))
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0512. Min Range: -2.0512
Max Act: 1.8733. Min Act: -0.1700
Data Index: 347843 (C4 (Web Text))
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0512. Min Range: -2.0512
Max Act: 1.8733. Min Act: -0.1700
Data Index: 582308 (C4 (Web Text))
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0512. Min Range: -2.0512
Max Act: 1.8647. Min Act: -0.1700
Data Index: 1249162 (C4 (Web Text))
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0512. Min Range: -2.0512
Max Act: 1.8733. Min Act: -0.1700
Data Index: 407304 (C4 (Web Text))
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #19