Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 168 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.0251. Min Range: -3.0251
Max Act: 3.0093. Min Act: -0.1700
Data Index: 94453 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0251. Min Range: -3.0251
Max Act: 3.0251. Min Act: -0.1700
Data Index: 1096086 (C4 (Web Text))
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0251. Min Range: -3.0251
Max Act: 2.9302. Min Act: -0.1700
Data Index: 145518 (C4 (Web Text))
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0251. Min Range: -3.0251
Max Act: 2.9618. Min Act: -0.1700
Data Index: 1102421 (C4 (Web Text))
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0251. Min Range: -3.0251
Max Act: 2.9143. Min Act: -0.1700
Data Index: 219666 (C4 (Web Text))
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0251. Min Range: -3.0251
Max Act: 2.9143. Min Act: -0.1700
Data Index: 989717 (C4 (Web Text))
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0251. Min Range: -3.0251
Max Act: 2.9143. Min Act: -0.1700
Data Index: 823782 (C4 (Web Text))
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0251. Min Range: -3.0251
Max Act: 2.9143. Min Act: -0.1700
Data Index: 1341694 (C4 (Web Text))
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0251. Min Range: -3.0251
Max Act: 2.8826. Min Act: -0.1700
Data Index: 83121 (C4 (Web Text))
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0251. Min Range: -3.0251
Max Act: 2.8985. Min Act: -0.1700
Data Index: 494333 (C4 (Web Text))
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0251. Min Range: -3.0251
Max Act: 2.9143. Min Act: -0.1700
Data Index: 675239 (C4 (Web Text))
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0251. Min Range: -3.0251
Max Act: 2.8667. Min Act: -0.1700
Data Index: 617807 (C4 (Web Text))
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0251. Min Range: -3.0251
Max Act: 2.8667. Min Act: -0.1700
Data Index: 1078502 (C4 (Web Text))
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0251. Min Range: -3.0251
Max Act: 2.8508. Min Act: -0.1700
Data Index: 525790 (C4 (Web Text))
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0251. Min Range: -3.0251
Max Act: 2.8667. Min Act: -0.1700
Data Index: 701185 (C4 (Web Text))
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0251. Min Range: -3.0251
Max Act: 2.8349. Min Act: -0.1700
Data Index: 139177 (C4 (Web Text))
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0251. Min Range: -3.0251
Max Act: 2.8031. Min Act: -0.1700
Data Index: 543460 (C4 (Web Text))
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0251. Min Range: -3.0251
Max Act: 2.8349. Min Act: -0.1700
Data Index: 1058621 (C4 (Web Text))
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0251. Min Range: -3.0251
Max Act: 2.8667. Min Act: -0.1700
Data Index: 160250 (C4 (Web Text))
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0251. Min Range: -3.0251
Max Act: 2.8508. Min Act: -0.1700
Data Index: 355469 (C4 (Web Text))
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #19