Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3148 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.8522. Min Range: -0.8522
Max Act: 0.8398. Min Act: -0.0001
Data Index: 838216 (C4 (Web Text))
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8522. Min Range: -0.8522
Max Act: 0.8522. Min Act: -0.0001
Data Index: 1173904 (C4 (Web Text))
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8522. Min Range: -0.8522
Max Act: 0.6741. Min Act: -0.0001
Data Index: 379025 (C4 (Web Text))
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8522. Min Range: -0.8522
Max Act: 0.7361. Min Act: -0.0001
Data Index: 293375 (C4 (Web Text))
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8522. Min Range: -0.8522
Max Act: 0.6350. Min Act: -0.0001
Data Index: 526294 (C4 (Web Text))
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8522. Min Range: -0.8522
Max Act: 0.5529. Min Act: -0.0001
Data Index: 921607 (C4 (Web Text))
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8522. Min Range: -0.8522
Max Act: 0.6336. Min Act: -0.0001
Data Index: 1437365 (Python Code)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8522. Min Range: -0.8522
Max Act: 0.6404. Min Act: -0.0001
Data Index: 571353 (C4 (Web Text))
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8522. Min Range: -0.8522
Max Act: 0.6078. Min Act: -0.0001
Data Index: 1558329 (Python Code)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8522. Min Range: -0.8522
Max Act: 0.6248. Min Act: -0.0001
Data Index: 1606085 (Python Code)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8522. Min Range: -0.8522
Max Act: 0.5975. Min Act: -0.0001
Data Index: 569779 (C4 (Web Text))
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8522. Min Range: -0.8522
Max Act: 0.5603. Min Act: -0.0000
Data Index: 1646588 (Python Code)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8522. Min Range: -0.8522
Max Act: 0.5961. Min Act: -0.0001
Data Index: 1480526 (Python Code)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8522. Min Range: -0.8522
Max Act: 0.6139. Min Act: -0.0001
Data Index: 1430476 (Python Code)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8522. Min Range: -0.8522
Max Act: 0.6126. Min Act: -0.0001
Data Index: 1360598 (Python Code)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8522. Min Range: -0.8522
Max Act: 0.5746. Min Act: -0.0001
Data Index: 1531157 (Python Code)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8522. Min Range: -0.8522
Max Act: 0.5755. Min Act: -0.0001
Data Index: 1570200 (Python Code)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8522. Min Range: -0.8522
Max Act: 0.5824. Min Act: -0.0001
Data Index: 1379096 (Python Code)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8522. Min Range: -0.8522
Max Act: 0.5995. Min Act: -0.0001
Data Index: 1397428 (Python Code)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8522. Min Range: -0.8522
Max Act: 0.6015. Min Act: -0.0001
Data Index: 1377316 (Python Code)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #19