Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1846 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.6980. Min Range: -3.6980
Max Act: 3.6980. Min Act: -0.1700
Data Index: 324097 (C4 (Web Text))
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6980. Min Range: -3.6980
Max Act: 3.6354. Min Act: -0.1700
Data Index: 540006 (C4 (Web Text))
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6980. Min Range: -3.6980
Max Act: 3.6354. Min Act: -0.1700
Data Index: 706767 (C4 (Web Text))
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6980. Min Range: -3.6980
Max Act: 3.6041. Min Act: -0.1700
Data Index: 550791 (C4 (Web Text))
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6980. Min Range: -3.6980
Max Act: 3.5728. Min Act: -0.1700
Data Index: 46699 (C4 (Web Text))
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6980. Min Range: -3.6980
Max Act: 3.5728. Min Act: -0.1700
Data Index: 956406 (C4 (Web Text))
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6980. Min Range: -3.6980
Max Act: 3.6041. Min Act: -0.1700
Data Index: 667923 (C4 (Web Text))
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6980. Min Range: -3.6980
Max Act: 3.5102. Min Act: -0.1700
Data Index: 108282 (C4 (Web Text))
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6980. Min Range: -3.6980
Max Act: 3.5415. Min Act: -0.1700
Data Index: 368029 (C4 (Web Text))
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6980. Min Range: -3.6980
Max Act: 3.5102. Min Act: -0.1700
Data Index: 304430 (C4 (Web Text))
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6980. Min Range: -3.6980
Max Act: 3.5415. Min Act: -0.1700
Data Index: 591377 (C4 (Web Text))
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6980. Min Range: -3.6980
Max Act: 3.5102. Min Act: -0.1700
Data Index: 1338324 (C4 (Web Text))
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6980. Min Range: -3.6980
Max Act: 3.5415. Min Act: -0.1700
Data Index: 1133474 (C4 (Web Text))
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6980. Min Range: -3.6980
Max Act: 3.4475. Min Act: -0.1700
Data Index: 1101100 (C4 (Web Text))
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6980. Min Range: -3.6980
Max Act: 3.4788. Min Act: -0.1700
Data Index: 317226 (C4 (Web Text))
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6980. Min Range: -3.6980
Max Act: 3.4475. Min Act: -0.1700
Data Index: 898961 (C4 (Web Text))
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6980. Min Range: -3.6980
Max Act: 3.4788. Min Act: -0.1700
Data Index: 459572 (C4 (Web Text))
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6980. Min Range: -3.6980
Max Act: 3.4475. Min Act: -0.1700
Data Index: 364596 (C4 (Web Text))
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6980. Min Range: -3.6980
Max Act: 3.4161. Min Act: -0.1700
Data Index: 799354 (C4 (Web Text))
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6980. Min Range: -3.6980
Max Act: 3.4788. Min Act: -0.1700
Data Index: 1087020 (C4 (Web Text))
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #19