Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 246 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.9129. Min Range: -2.9129
Max Act: 2.9129. Min Act: -0.1700
Data Index: 1384988 (Python Code)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9129. Min Range: -2.9129
Max Act: 2.8971. Min Act: -0.1700
Data Index: 386607 (C4 (Web Text))
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9129. Min Range: -2.9129
Max Act: 2.8812. Min Act: -0.1700
Data Index: 1188843 (C4 (Web Text))
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9129. Min Range: -2.9129
Max Act: 2.8653. Min Act: -0.1700
Data Index: 67612 (C4 (Web Text))
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9129. Min Range: -2.9129
Max Act: 2.8812. Min Act: -0.1700
Data Index: 1399744 (Python Code)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9129. Min Range: -2.9129
Max Act: 2.8653. Min Act: -0.1700
Data Index: 1531276 (Python Code)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9129. Min Range: -2.9129
Max Act: 2.8653. Min Act: -0.1700
Data Index: 893490 (C4 (Web Text))
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9129. Min Range: -2.9129
Max Act: 2.8653. Min Act: -0.1700
Data Index: 177123 (C4 (Web Text))
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9129. Min Range: -2.9129
Max Act: 2.8653. Min Act: -0.1700
Data Index: 1598509 (Python Code)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9129. Min Range: -2.9129
Max Act: 2.8494. Min Act: -0.1700
Data Index: 1510641 (Python Code)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9129. Min Range: -2.9129
Max Act: 2.8494. Min Act: -0.1700
Data Index: 1490857 (Python Code)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9129. Min Range: -2.9129
Max Act: 2.8494. Min Act: -0.1700
Data Index: 1227564 (C4 (Web Text))
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9129. Min Range: -2.9129
Max Act: 2.8494. Min Act: -0.1700
Data Index: 765527 (C4 (Web Text))
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9129. Min Range: -2.9129
Max Act: 2.8176. Min Act: -0.1700
Data Index: 49434 (C4 (Web Text))
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9129. Min Range: -2.9129
Max Act: 2.8494. Min Act: -0.1700
Data Index: 956399 (C4 (Web Text))
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9129. Min Range: -2.9129
Max Act: 2.8176. Min Act: -0.1700
Data Index: 1635379 (Python Code)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9129. Min Range: -2.9129
Max Act: 2.8176. Min Act: -0.1700
Data Index: 979581 (C4 (Web Text))
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9129. Min Range: -2.9129
Max Act: 2.8017. Min Act: -0.1700
Data Index: 23170 (C4 (Web Text))
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9129. Min Range: -2.9129
Max Act: 2.8017. Min Act: -0.1700
Data Index: 1645538 (Python Code)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9129. Min Range: -2.9129
Max Act: 2.8017. Min Act: -0.1700
Data Index: 760788 (C4 (Web Text))
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #19