Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1990 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.0106. Min Range: -4.0106
Max Act: 4.0106. Min Act: -0.1700
Data Index: 982002 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0106. Min Range: -4.0106
Max Act: 4.0106. Min Act: -0.1700
Data Index: 696070 (C4 (Web Text))
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0106. Min Range: -4.0106
Max Act: 3.9168. Min Act: -0.1700
Data Index: 608292 (C4 (Web Text))
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0106. Min Range: -4.0106
Max Act: 3.9481. Min Act: -0.1700
Data Index: 1089206 (C4 (Web Text))
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0106. Min Range: -4.0106
Max Act: 3.8230. Min Act: -0.1700
Data Index: 387307 (C4 (Web Text))
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0106. Min Range: -4.0106
Max Act: 3.7917. Min Act: -0.1700
Data Index: 1002439 (C4 (Web Text))
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0106. Min Range: -4.0106
Max Act: 3.7917. Min Act: -0.1700
Data Index: 605792 (C4 (Web Text))
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0106. Min Range: -4.0106
Max Act: 3.8543. Min Act: -0.1700
Data Index: 1321853 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0106. Min Range: -4.0106
Max Act: 3.7917. Min Act: -0.1700
Data Index: 698964 (C4 (Web Text))
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0106. Min Range: -4.0106
Max Act: 3.8230. Min Act: -0.1700
Data Index: 152807 (C4 (Web Text))
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0106. Min Range: -4.0106
Max Act: 3.7917. Min Act: -0.1700
Data Index: 761178 (C4 (Web Text))
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0106. Min Range: -4.0106
Max Act: 3.8543. Min Act: -0.1700
Data Index: 464016 (C4 (Web Text))
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0106. Min Range: -4.0106
Max Act: 3.7604. Min Act: -0.1700
Data Index: 627786 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0106. Min Range: -4.0106
Max Act: 3.7291. Min Act: -0.1700
Data Index: 1268311 (C4 (Web Text))
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0106. Min Range: -4.0106
Max Act: 3.7917. Min Act: -0.1700
Data Index: 1012333 (C4 (Web Text))
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0106. Min Range: -4.0106
Max Act: 3.7604. Min Act: -0.1700
Data Index: 1154365 (C4 (Web Text))
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0106. Min Range: -4.0106
Max Act: 3.6665. Min Act: -0.1700
Data Index: 1123200 (C4 (Web Text))
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0106. Min Range: -4.0106
Max Act: 3.7917. Min Act: -0.1700
Data Index: 1116138 (C4 (Web Text))
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0106. Min Range: -4.0106
Max Act: 3.6665. Min Act: -0.1700
Data Index: 383695 (C4 (Web Text))
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0106. Min Range: -4.0106
Max Act: 3.7604. Min Act: -0.1700
Data Index: 143742 (C4 (Web Text))
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #19