Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 20 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 5.0455. Min Range: -5.0455
Max Act: 4.9518. Min Act: -0.1700
Data Index: 1032509 (C4 (Web Text))
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0455. Min Range: -5.0455
Max Act: 5.0455. Min Act: -0.1700
Data Index: 1416521 (Python Code)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0455. Min Range: -5.0455
Max Act: 5.0143. Min Act: -0.1700
Data Index: 242571 (C4 (Web Text))
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0455. Min Range: -5.0455
Max Act: 5.0143. Min Act: -0.1700
Data Index: 573684 (C4 (Web Text))
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0455. Min Range: -5.0455
Max Act: 5.0143. Min Act: -0.1700
Data Index: 1254664 (C4 (Web Text))
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0455. Min Range: -5.0455
Max Act: 4.9830. Min Act: -0.1700
Data Index: 1442808 (Python Code)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0455. Min Range: -5.0455
Max Act: 4.9518. Min Act: -0.1700
Data Index: 625176 (C4 (Web Text))
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0455. Min Range: -5.0455
Max Act: 4.9205. Min Act: -0.1700
Data Index: 1303829 (C4 (Web Text))
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0455. Min Range: -5.0455
Max Act: 4.9518. Min Act: -0.1700
Data Index: 1295847 (C4 (Web Text))
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0455. Min Range: -5.0455
Max Act: 5.0143. Min Act: -0.1700
Data Index: 345626 (C4 (Web Text))
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0455. Min Range: -5.0455
Max Act: 4.9830. Min Act: -0.1700
Data Index: 244723 (C4 (Web Text))
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0455. Min Range: -5.0455
Max Act: 4.9518. Min Act: -0.1700
Data Index: 1656430 (Python Code)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0455. Min Range: -5.0455
Max Act: 5.0143. Min Act: -0.1700
Data Index: 1588946 (Python Code)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0455. Min Range: -5.0455
Max Act: 4.9205. Min Act: -0.1700
Data Index: 1016493 (C4 (Web Text))
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0455. Min Range: -5.0455
Max Act: 4.8580. Min Act: -0.1700
Data Index: 1012106 (C4 (Web Text))
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0455. Min Range: -5.0455
Max Act: 4.9205. Min Act: -0.1700
Data Index: 1612302 (Python Code)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0455. Min Range: -5.0455
Max Act: 4.9205. Min Act: -0.1699
Data Index: 1386651 (Python Code)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0455. Min Range: -5.0455
Max Act: 4.8893. Min Act: -0.1700
Data Index: 563555 (C4 (Web Text))
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0455. Min Range: -5.0455
Max Act: 4.8580. Min Act: -0.1700
Data Index: 1148122 (C4 (Web Text))
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0455. Min Range: -5.0455
Max Act: 4.9205. Min Act: -0.1700
Data Index: 466651 (C4 (Web Text))
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #19