Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1947 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.4013. Min Range: -2.4013
Max Act: 2.4013. Min Act: -0.1700
Data Index: 999056 (C4 (Web Text))
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4013. Min Range: -2.4013
Max Act: 2.3850. Min Act: -0.1700
Data Index: 644462 (C4 (Web Text))
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4013. Min Range: -2.4013
Max Act: 2.3359. Min Act: -0.1700
Data Index: 189957 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4013. Min Range: -2.4013
Max Act: 2.3359. Min Act: -0.1700
Data Index: 360453 (C4 (Web Text))
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4013. Min Range: -2.4013
Max Act: 2.3523. Min Act: -0.1700
Data Index: 1239932 (C4 (Web Text))
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4013. Min Range: -2.4013
Max Act: 2.3195. Min Act: -0.1700
Data Index: 524681 (C4 (Web Text))
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4013. Min Range: -2.4013
Max Act: 2.3031. Min Act: -0.1700
Data Index: 672490 (C4 (Web Text))
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4013. Min Range: -2.4013
Max Act: 2.3359. Min Act: -0.1700
Data Index: 53228 (C4 (Web Text))
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4013. Min Range: -2.4013
Max Act: 2.3195. Min Act: -0.1700
Data Index: 492550 (C4 (Web Text))
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4013. Min Range: -2.4013
Max Act: 2.3031. Min Act: -0.1700
Data Index: 416042 (C4 (Web Text))
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4013. Min Range: -2.4013
Max Act: 2.2866. Min Act: -0.1700
Data Index: 1387897 (Python Code)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4013. Min Range: -2.4013
Max Act: 2.2866. Min Act: -0.1700
Data Index: 1060812 (C4 (Web Text))
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4013. Min Range: -2.4013
Max Act: 2.2866. Min Act: -0.1700
Data Index: 1090804 (C4 (Web Text))
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4013. Min Range: -2.4013
Max Act: 2.3031. Min Act: -0.1700
Data Index: 1164219 (C4 (Web Text))
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4013. Min Range: -2.4013
Max Act: 2.2866. Min Act: -0.1700
Data Index: 1002714 (C4 (Web Text))
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4013. Min Range: -2.4013
Max Act: 2.2702. Min Act: -0.1700
Data Index: 1227044 (C4 (Web Text))
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4013. Min Range: -2.4013
Max Act: 2.2866. Min Act: -0.1700
Data Index: 1127287 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4013. Min Range: -2.4013
Max Act: 2.2702. Min Act: -0.1700
Data Index: 664142 (C4 (Web Text))
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4013. Min Range: -2.4013
Max Act: 2.2866. Min Act: -0.1700
Data Index: 1004062 (C4 (Web Text))
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4013. Min Range: -2.4013
Max Act: 2.2702. Min Act: -0.1700
Data Index: 771182 (C4 (Web Text))
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #19