Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2017 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.5115. Min Range: -4.5115
Max Act: 4.5115. Min Act: -0.1700
Data Index: 976827 (C4 (Web Text))
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5115. Min Range: -4.5115
Max Act: 4.4177. Min Act: -0.1700
Data Index: 200549 (C4 (Web Text))
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5115. Min Range: -4.5115
Max Act: 4.4177. Min Act: -0.1700
Data Index: 205258 (C4 (Web Text))
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5115. Min Range: -4.5115
Max Act: 4.4802. Min Act: -0.1700
Data Index: 251253 (C4 (Web Text))
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5115. Min Range: -4.5115
Max Act: 4.3865. Min Act: -0.1700
Data Index: 646702 (C4 (Web Text))
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5115. Min Range: -4.5115
Max Act: 4.4490. Min Act: -0.1700
Data Index: 1309984 (C4 (Web Text))
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5115. Min Range: -4.5115
Max Act: 4.3865. Min Act: -0.1700
Data Index: 749228 (C4 (Web Text))
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5115. Min Range: -4.5115
Max Act: 4.3865. Min Act: -0.1700
Data Index: 936397 (C4 (Web Text))
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5115. Min Range: -4.5115
Max Act: 4.3552. Min Act: -0.1700
Data Index: 88858 (C4 (Web Text))
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5115. Min Range: -4.5115
Max Act: 4.3240. Min Act: -0.1700
Data Index: 302094 (C4 (Web Text))
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5115. Min Range: -4.5115
Max Act: 4.3552. Min Act: -0.1700
Data Index: 725619 (C4 (Web Text))
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5115. Min Range: -4.5115
Max Act: 4.3552. Min Act: -0.1700
Data Index: 304898 (C4 (Web Text))
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5115. Min Range: -4.5115
Max Act: 4.3240. Min Act: -0.1700
Data Index: 362043 (C4 (Web Text))
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5115. Min Range: -4.5115
Max Act: 4.3240. Min Act: -0.1700
Data Index: 122986 (C4 (Web Text))
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5115. Min Range: -4.5115
Max Act: 4.2927. Min Act: -0.1700
Data Index: 530132 (C4 (Web Text))
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5115. Min Range: -4.5115
Max Act: 4.2927. Min Act: -0.1700
Data Index: 168364 (C4 (Web Text))
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5115. Min Range: -4.5115
Max Act: 4.2615. Min Act: -0.1700
Data Index: 74783 (C4 (Web Text))
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5115. Min Range: -4.5115
Max Act: 4.2927. Min Act: -0.1700
Data Index: 937442 (C4 (Web Text))
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5115. Min Range: -4.5115
Max Act: 4.2927. Min Act: -0.1700
Data Index: 540829 (C4 (Web Text))
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5115. Min Range: -4.5115
Max Act: 4.2302. Min Act: -0.1700
Data Index: 827950 (C4 (Web Text))
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #19