Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2010 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.5460. Min Range: -4.5460
Max Act: 4.5460. Min Act: -0.1700
Data Index: 825017 (C4 (Web Text))
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5460. Min Range: -4.5460
Max Act: 4.5460. Min Act: -0.1700
Data Index: 356 (C4 (Web Text))
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5460. Min Range: -4.5460
Max Act: 4.4522. Min Act: -0.1700
Data Index: 13631 (C4 (Web Text))
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5460. Min Range: -4.5460
Max Act: 4.5460. Min Act: -0.1700
Data Index: 897085 (C4 (Web Text))
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5460. Min Range: -4.5460
Max Act: 4.4678. Min Act: -0.1700
Data Index: 1019938 (C4 (Web Text))
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5460. Min Range: -4.5460
Max Act: 4.4835. Min Act: -0.1700
Data Index: 734882 (C4 (Web Text))
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5460. Min Range: -4.5460
Max Act: 4.4678. Min Act: -0.1700
Data Index: 820920 (C4 (Web Text))
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5460. Min Range: -4.5460
Max Act: 4.3897. Min Act: -0.1700
Data Index: 845891 (C4 (Web Text))
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5460. Min Range: -4.5460
Max Act: 4.3741. Min Act: -0.1700
Data Index: 1136267 (C4 (Web Text))
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5460. Min Range: -4.5460
Max Act: 4.4053. Min Act: -0.1700
Data Index: 289333 (C4 (Web Text))
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5460. Min Range: -4.5460
Max Act: 4.4209. Min Act: -0.1700
Data Index: 187253 (C4 (Web Text))
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5460. Min Range: -4.5460
Max Act: 4.3741. Min Act: -0.1700
Data Index: 630217 (C4 (Web Text))
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5460. Min Range: -4.5460
Max Act: 4.3741. Min Act: -0.1700
Data Index: 774272 (C4 (Web Text))
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5460. Min Range: -4.5460
Max Act: 4.3428. Min Act: -0.1700
Data Index: 1228553 (C4 (Web Text))
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5460. Min Range: -4.5460
Max Act: 4.3741. Min Act: -0.1700
Data Index: 919032 (C4 (Web Text))
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5460. Min Range: -4.5460
Max Act: 4.3584. Min Act: -0.1700
Data Index: 458276 (C4 (Web Text))
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5460. Min Range: -4.5460
Max Act: 4.3741. Min Act: -0.1700
Data Index: 252134 (C4 (Web Text))
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5460. Min Range: -4.5460
Max Act: 4.3741. Min Act: -0.1700
Data Index: 432305 (C4 (Web Text))
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5460. Min Range: -4.5460
Max Act: 4.3116. Min Act: -0.1700
Data Index: 18629 (C4 (Web Text))
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5460. Min Range: -4.5460
Max Act: 4.3741. Min Act: -0.1700
Data Index: 736361 (C4 (Web Text))
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #19