Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 260 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 6.6875. Min Range: -6.6875
Max Act: 6.6875. Min Act: -0.1700
Data Index: 784590 (C4 (Web Text))
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6875. Min Range: -6.6875
Max Act: 6.6094. Min Act: -0.1700
Data Index: 251471 (C4 (Web Text))
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6875. Min Range: -6.6875
Max Act: 6.5312. Min Act: -0.1700
Data Index: 1342905 (C4 (Web Text))
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6875. Min Range: -6.6875
Max Act: 6.4844. Min Act: -0.1700
Data Index: 1341685 (C4 (Web Text))
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6875. Min Range: -6.6875
Max Act: 6.3125. Min Act: -0.1700
Data Index: 168583 (C4 (Web Text))
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6875. Min Range: -6.6875
Max Act: 6.3594. Min Act: -0.1700
Data Index: 759419 (C4 (Web Text))
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6875. Min Range: -6.6875
Max Act: 6.2969. Min Act: -0.1700
Data Index: 928814 (C4 (Web Text))
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6875. Min Range: -6.6875
Max Act: 6.2656. Min Act: -0.1700
Data Index: 1267126 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6875. Min Range: -6.6875
Max Act: 6.2187. Min Act: -0.1700
Data Index: 361583 (C4 (Web Text))
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6875. Min Range: -6.6875
Max Act: 6.2031. Min Act: -0.1700
Data Index: 805647 (C4 (Web Text))
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6875. Min Range: -6.6875
Max Act: 6.0937. Min Act: -0.1700
Data Index: 1373848 (Python Code)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6875. Min Range: -6.6875
Max Act: 6.1719. Min Act: -0.1700
Data Index: 849985 (C4 (Web Text))
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6875. Min Range: -6.6875
Max Act: 6.2031. Min Act: -0.1700
Data Index: 662997 (C4 (Web Text))
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6875. Min Range: -6.6875
Max Act: 6.0937. Min Act: -0.1700
Data Index: 421530 (C4 (Web Text))
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6875. Min Range: -6.6875
Max Act: 6.1250. Min Act: -0.1700
Data Index: 642899 (C4 (Web Text))
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6875. Min Range: -6.6875
Max Act: 6.1250. Min Act: -0.1700
Data Index: 880388 (C4 (Web Text))
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6875. Min Range: -6.6875
Max Act: 6.0625. Min Act: -0.1699
Data Index: 568660 (C4 (Web Text))
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6875. Min Range: -6.6875
Max Act: 6.1406. Min Act: -0.1700
Data Index: 1021365 (C4 (Web Text))
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6875. Min Range: -6.6875
Max Act: 6.0937. Min Act: -0.1700
Data Index: 1294934 (C4 (Web Text))
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6875. Min Range: -6.6875
Max Act: 6.1250. Min Act: -0.1690
Data Index: 172867 (C4 (Web Text))
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #19