Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1712 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 3.1482. Min Range: -3.1482
Max Act: 3.1482. Min Act: -0.1700
Data Index: 1155748 (C4 (Web Text))
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1482. Min Range: -3.1482
Max Act: 3.1010. Min Act: -0.1700
Data Index: 968360 (C4 (Web Text))
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1482. Min Range: -3.1482
Max Act: 3.0536. Min Act: -0.1700
Data Index: 1086895 (C4 (Web Text))
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1482. Min Range: -3.1482
Max Act: 3.0221. Min Act: -0.1700
Data Index: 934647 (C4 (Web Text))
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1482. Min Range: -3.1482
Max Act: 3.0221. Min Act: -0.1700
Data Index: 262859 (C4 (Web Text))
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1482. Min Range: -3.1482
Max Act: 3.0063. Min Act: -0.1700
Data Index: 613856 (C4 (Web Text))
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1482. Min Range: -3.1482
Max Act: 2.9904. Min Act: -0.1700
Data Index: 1179012 (C4 (Web Text))
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1482. Min Range: -3.1482
Max Act: 2.9588. Min Act: -0.1700
Data Index: 52857 (C4 (Web Text))
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1482. Min Range: -3.1482
Max Act: 2.9588. Min Act: -0.1700
Data Index: 297658 (C4 (Web Text))
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1482. Min Range: -3.1482
Max Act: 2.9271. Min Act: -0.1700
Data Index: 575545 (C4 (Web Text))
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1482. Min Range: -3.1482
Max Act: 2.9430. Min Act: -0.1700
Data Index: 658295 (C4 (Web Text))
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1482. Min Range: -3.1482
Max Act: 2.9430. Min Act: -0.1700
Data Index: 1285473 (C4 (Web Text))
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1482. Min Range: -3.1482
Max Act: 2.9271. Min Act: -0.1700
Data Index: 970318 (C4 (Web Text))
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1482. Min Range: -3.1482
Max Act: 2.9113. Min Act: -0.1700
Data Index: 480270 (C4 (Web Text))
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1482. Min Range: -3.1482
Max Act: 2.9113. Min Act: -0.1700
Data Index: 1247056 (C4 (Web Text))
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1482. Min Range: -3.1482
Max Act: 2.9113. Min Act: -0.1700
Data Index: 1307171 (C4 (Web Text))
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1482. Min Range: -3.1482
Max Act: 2.8954. Min Act: -0.1700
Data Index: 1033951 (C4 (Web Text))
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1482. Min Range: -3.1482
Max Act: 2.9113. Min Act: -0.1700
Data Index: 677987 (C4 (Web Text))
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1482. Min Range: -3.1482
Max Act: 2.8954. Min Act: -0.1700
Data Index: 284673 (C4 (Web Text))
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1482. Min Range: -3.1482
Max Act: 2.8795. Min Act: -0.1700
Data Index: 93624 (C4 (Web Text))
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #19