Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 142 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.1481. Min Range: -4.1481
Max Act: 4.1481. Min Act: -0.1700
Data Index: 14922 (C4 (Web Text))
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1481. Min Range: -4.1481
Max Act: 4.1481. Min Act: -0.1700
Data Index: 289432 (C4 (Web Text))
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1481. Min Range: -4.1481
Max Act: 4.1481. Min Act: -0.1700
Data Index: 266860 (C4 (Web Text))
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1481. Min Range: -4.1481
Max Act: 4.1169. Min Act: -0.1700
Data Index: 437136 (C4 (Web Text))
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1481. Min Range: -4.1481
Max Act: 4.0856. Min Act: -0.1700
Data Index: 164445 (C4 (Web Text))
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1481. Min Range: -4.1481
Max Act: 4.0543. Min Act: -0.1700
Data Index: 622117 (C4 (Web Text))
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1481. Min Range: -4.1481
Max Act: 4.0231. Min Act: -0.1700
Data Index: 759787 (C4 (Web Text))
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1481. Min Range: -4.1481
Max Act: 3.9762. Min Act: -0.1700
Data Index: 991568 (C4 (Web Text))
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1481. Min Range: -4.1481
Max Act: 3.9918. Min Act: -0.1700
Data Index: 698764 (C4 (Web Text))
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1481. Min Range: -4.1481
Max Act: 4.0075. Min Act: -0.1700
Data Index: 612871 (C4 (Web Text))
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1481. Min Range: -4.1481
Max Act: 3.9762. Min Act: -0.1700
Data Index: 1280708 (C4 (Web Text))
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1481. Min Range: -4.1481
Max Act: 3.9918. Min Act: -0.1700
Data Index: 953118 (C4 (Web Text))
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1481. Min Range: -4.1481
Max Act: 3.9606. Min Act: -0.1700
Data Index: 127355 (C4 (Web Text))
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1481. Min Range: -4.1481
Max Act: 3.9606. Min Act: -0.1700
Data Index: 606250 (C4 (Web Text))
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1481. Min Range: -4.1481
Max Act: 3.9762. Min Act: -0.1700
Data Index: 925976 (C4 (Web Text))
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1481. Min Range: -4.1481
Max Act: 3.9606. Min Act: -0.1700
Data Index: 654174 (C4 (Web Text))
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1481. Min Range: -4.1481
Max Act: 3.9762. Min Act: -0.1700
Data Index: 1082992 (C4 (Web Text))
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1481. Min Range: -4.1481
Max Act: 3.9293. Min Act: -0.1700
Data Index: 965613 (C4 (Web Text))
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1481. Min Range: -4.1481
Max Act: 3.9762. Min Act: -0.1700
Data Index: 789027 (C4 (Web Text))
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1481. Min Range: -4.1481
Max Act: 3.9606. Min Act: -0.1700
Data Index: 518161 (C4 (Web Text))
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #19