Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 20 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.7796. Min Range: -2.7796
Max Act: 2.7796. Min Act: -0.0001
Data Index: 605997 (C4 (Web Text))
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7796. Min Range: -2.7796
Max Act: 2.4839. Min Act: -0.0001
Data Index: 782812 (C4 (Web Text))
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7796. Min Range: -2.7796
Max Act: 2.3744. Min Act: -0.0001
Data Index: 491508 (C4 (Web Text))
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7796. Min Range: -2.7796
Max Act: 2.0573. Min Act: -0.0001
Data Index: 941581 (C4 (Web Text))
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7796. Min Range: -2.7796
Max Act: 2.1139. Min Act: -0.0001
Data Index: 5004 (C4 (Web Text))
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7796. Min Range: -2.7796
Max Act: 2.1664. Min Act: -0.0001
Data Index: 1207284 (C4 (Web Text))
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7796. Min Range: -2.7796
Max Act: 1.9269. Min Act: -0.0001
Data Index: 312732 (C4 (Web Text))
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7796. Min Range: -2.7796
Max Act: 2.0204. Min Act: -0.0001
Data Index: 616736 (C4 (Web Text))
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7796. Min Range: -2.7796
Max Act: 2.0059. Min Act: -0.0001
Data Index: 426867 (C4 (Web Text))
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7796. Min Range: -2.7796
Max Act: 2.0817. Min Act: -0.0001
Data Index: 1223374 (C4 (Web Text))
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7796. Min Range: -2.7796
Max Act: 1.8856. Min Act: -0.0001
Data Index: 1155393 (C4 (Web Text))
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7796. Min Range: -2.7796
Max Act: 1.9555. Min Act: -0.0001
Data Index: 1323817 (C4 (Web Text))
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7796. Min Range: -2.7796
Max Act: 1.9273. Min Act: -0.0001
Data Index: 282903 (C4 (Web Text))
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7796. Min Range: -2.7796
Max Act: 1.8658. Min Act: -0.0001
Data Index: 1101390 (C4 (Web Text))
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7796. Min Range: -2.7796
Max Act: 1.9729. Min Act: -0.0001
Data Index: 675483 (C4 (Web Text))
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7796. Min Range: -2.7796
Max Act: 1.7489. Min Act: -0.0001
Data Index: 1226404 (C4 (Web Text))
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7796. Min Range: -2.7796
Max Act: 1.8905. Min Act: -0.0001
Data Index: 160919 (C4 (Web Text))
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7796. Min Range: -2.7796
Max Act: 1.8884. Min Act: -0.0001
Data Index: 1184270 (C4 (Web Text))
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7796. Min Range: -2.7796
Max Act: 1.9647. Min Act: -0.0001
Data Index: 364462 (C4 (Web Text))
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7796. Min Range: -2.7796
Max Act: 1.9104. Min Act: -0.0001
Data Index: 24428 (C4 (Web Text))
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #19