Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1959 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.8867. Min Range: -2.8867
Max Act: 2.8867. Min Act: -0.1700
Data Index: 1090842 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8867. Min Range: -2.8867
Max Act: 2.7275. Min Act: -0.1700
Data Index: 1111263 (C4 (Web Text))
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8867. Min Range: -2.8867
Max Act: 2.6955. Min Act: -0.1700
Data Index: 8586 (C4 (Web Text))
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8867. Min Range: -2.8867
Max Act: 2.6795. Min Act: -0.1700
Data Index: 399965 (C4 (Web Text))
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8867. Min Range: -2.8867
Max Act: 2.6795. Min Act: -0.1700
Data Index: 677872 (C4 (Web Text))
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8867. Min Range: -2.8867
Max Act: 2.6795. Min Act: -0.1700
Data Index: 1131567 (C4 (Web Text))
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8867. Min Range: -2.8867
Max Act: 2.6635. Min Act: -0.1700
Data Index: 1355241 (C4 (Web Text))
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8867. Min Range: -2.8867
Max Act: 2.6795. Min Act: -0.1700
Data Index: 1345062 (C4 (Web Text))
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8867. Min Range: -2.8867
Max Act: 2.6635. Min Act: -0.1700
Data Index: 92033 (C4 (Web Text))
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8867. Min Range: -2.8867
Max Act: 2.6635. Min Act: -0.1700
Data Index: 1228244 (C4 (Web Text))
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8867. Min Range: -2.8867
Max Act: 2.6795. Min Act: -0.1700
Data Index: 749770 (C4 (Web Text))
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8867. Min Range: -2.8867
Max Act: 2.6475. Min Act: -0.1700
Data Index: 220401 (C4 (Web Text))
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8867. Min Range: -2.8867
Max Act: 2.6314. Min Act: -0.1700
Data Index: 1120317 (C4 (Web Text))
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8867. Min Range: -2.8867
Max Act: 2.6475. Min Act: -0.1700
Data Index: 519463 (C4 (Web Text))
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8867. Min Range: -2.8867
Max Act: 2.6475. Min Act: -0.1700
Data Index: 1195539 (C4 (Web Text))
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8867. Min Range: -2.8867
Max Act: 2.6314. Min Act: -0.1700
Data Index: 1161410 (C4 (Web Text))
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8867. Min Range: -2.8867
Max Act: 2.6475. Min Act: -0.1700
Data Index: 1130558 (C4 (Web Text))
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8867. Min Range: -2.8867
Max Act: 2.5992. Min Act: -0.1700
Data Index: 846869 (C4 (Web Text))
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8867. Min Range: -2.8867
Max Act: 2.5992. Min Act: -0.1700
Data Index: 1098070 (C4 (Web Text))
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8867. Min Range: -2.8867
Max Act: 2.6153. Min Act: -0.1700
Data Index: 1101924 (C4 (Web Text))
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #19