Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2978 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.0500. Min Range: -0.0500
Max Act: 0.0500. Min Act: -0.0001
Data Index: 899460 (C4 (Web Text))
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0500. Min Range: -0.0500
Max Act: 0.0420. Min Act: -0.0001
Data Index: 1393718 (Python Code)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0500. Min Range: -0.0500
Max Act: 0.0464. Min Act: -0.0001
Data Index: 1234330 (C4 (Web Text))
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0500. Min Range: -0.0500
Max Act: 0.0395. Min Act: -0.0001
Data Index: 1384809 (Python Code)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0500. Min Range: -0.0500
Max Act: 0.0410. Min Act: -0.0001
Data Index: 808518 (C4 (Web Text))
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0500. Min Range: -0.0500
Max Act: 0.0323. Min Act: -0.0001
Data Index: 1648462 (Python Code)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0500. Min Range: -0.0500
Max Act: 0.0421. Min Act: -0.0001
Data Index: 1021732 (C4 (Web Text))
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0500. Min Range: -0.0500
Max Act: 0.0420. Min Act: -0.0001
Data Index: 953858 (C4 (Web Text))
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0500. Min Range: -0.0500
Max Act: 0.0363. Min Act: -0.0001
Data Index: 1541417 (Python Code)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0500. Min Range: -0.0500
Max Act: 0.0329. Min Act: -0.0002
Data Index: 1411373 (Python Code)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0500. Min Range: -0.0500
Max Act: 0.0434. Min Act: -0.0001
Data Index: 1444991 (Python Code)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0500. Min Range: -0.0500
Max Act: 0.0353. Min Act: -0.0001
Data Index: 362599 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0500. Min Range: -0.0500
Max Act: 0.0410. Min Act: -0.0001
Data Index: 1553281 (Python Code)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0500. Min Range: -0.0500
Max Act: 0.0407. Min Act: -0.0001
Data Index: 1456633 (Python Code)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0500. Min Range: -0.0500
Max Act: 0.0427. Min Act: -0.0001
Data Index: 1319522 (C4 (Web Text))
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0500. Min Range: -0.0500
Max Act: 0.0367. Min Act: -0.0001
Data Index: 1497186 (Python Code)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0500. Min Range: -0.0500
Max Act: 0.0324. Min Act: -0.0001
Data Index: 426776 (C4 (Web Text))
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0500. Min Range: -0.0500
Max Act: 0.0303. Min Act: -0.0001
Data Index: 1565349 (Python Code)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0500. Min Range: -0.0500
Max Act: 0.0363. Min Act: -0.0001
Data Index: 714491 (C4 (Web Text))
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0500. Min Range: -0.0500
Max Act: 0.0379. Min Act: -0.0001
Data Index: 492167 (C4 (Web Text))
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #19