Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2439 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 3.2165. Min Range: -3.2165
Max Act: 3.2165. Min Act: -0.0001
Data Index: 671959 (C4 (Web Text))
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2165. Min Range: -3.2165
Max Act: 2.9576. Min Act: -0.0001
Data Index: 371975 (C4 (Web Text))
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2165. Min Range: -3.2165
Max Act: 2.2420. Min Act: -0.0001
Data Index: 229343 (C4 (Web Text))
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2165. Min Range: -3.2165
Max Act: 2.2833. Min Act: -0.0001
Data Index: 547275 (C4 (Web Text))
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2165. Min Range: -3.2165
Max Act: 2.2797. Min Act: -0.0001
Data Index: 1116860 (C4 (Web Text))
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2165. Min Range: -3.2165
Max Act: 2.1765. Min Act: -0.0001
Data Index: 314511 (C4 (Web Text))
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2165. Min Range: -3.2165
Max Act: 2.2503. Min Act: -0.0001
Data Index: 18585 (C4 (Web Text))
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2165. Min Range: -3.2165
Max Act: 2.1100. Min Act: -0.0001
Data Index: 126816 (C4 (Web Text))
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2165. Min Range: -3.2165
Max Act: 2.1073. Min Act: -0.0001
Data Index: 345308 (C4 (Web Text))
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2165. Min Range: -3.2165
Max Act: 2.0985. Min Act: -0.0001
Data Index: 1079742 (C4 (Web Text))
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2165. Min Range: -3.2165
Max Act: 2.1344. Min Act: -0.0001
Data Index: 411893 (C4 (Web Text))
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2165. Min Range: -3.2165
Max Act: 2.1978. Min Act: -0.0001
Data Index: 458702 (C4 (Web Text))
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2165. Min Range: -3.2165
Max Act: 2.1193. Min Act: -0.0001
Data Index: 735556 (C4 (Web Text))
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2165. Min Range: -3.2165
Max Act: 2.1765. Min Act: -0.0001
Data Index: 520480 (C4 (Web Text))
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2165. Min Range: -3.2165
Max Act: 2.2456. Min Act: -0.0001
Data Index: 632573 (C4 (Web Text))
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2165. Min Range: -3.2165
Max Act: 2.1619. Min Act: -0.0001
Data Index: 887145 (C4 (Web Text))
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2165. Min Range: -3.2165
Max Act: 2.1389. Min Act: -0.0001
Data Index: 1228392 (C4 (Web Text))
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2165. Min Range: -3.2165
Max Act: 2.1019. Min Act: -0.0001
Data Index: 681086 (C4 (Web Text))
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2165. Min Range: -3.2165
Max Act: 2.0177. Min Act: -0.0001
Data Index: 1295521 (C4 (Web Text))
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2165. Min Range: -3.2165
Max Act: 2.2373. Min Act: -0.0001
Data Index: 76485 (C4 (Web Text))
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #19