Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2444 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.5269. Min Range: -1.5269
Max Act: 1.5269. Min Act: -0.0001
Data Index: 1517063 (Python Code)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5269. Min Range: -1.5269
Max Act: 1.4142. Min Act: -0.0001
Data Index: 1303381 (C4 (Web Text))
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5269. Min Range: -1.5269
Max Act: 1.4133. Min Act: -0.0001
Data Index: 37851 (C4 (Web Text))
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5269. Min Range: -1.5269
Max Act: 1.5221. Min Act: -0.0001
Data Index: 911215 (C4 (Web Text))
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5269. Min Range: -1.5269
Max Act: 1.3686. Min Act: -0.0001
Data Index: 846061 (C4 (Web Text))
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5269. Min Range: -1.5269
Max Act: 1.3120. Min Act: -0.0001
Data Index: 995813 (C4 (Web Text))
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5269. Min Range: -1.5269
Max Act: 1.2066. Min Act: -0.0001
Data Index: 802372 (C4 (Web Text))
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5269. Min Range: -1.5269
Max Act: 1.3631. Min Act: -0.0001
Data Index: 1275059 (C4 (Web Text))
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5269. Min Range: -1.5269
Max Act: 1.2607. Min Act: -0.0001
Data Index: 1326337 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5269. Min Range: -1.5269
Max Act: 1.2923. Min Act: -0.0001
Data Index: 663771 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5269. Min Range: -1.5269
Max Act: 1.2915. Min Act: -0.0001
Data Index: 968112 (C4 (Web Text))
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5269. Min Range: -1.5269
Max Act: 1.1882. Min Act: -0.0001
Data Index: 21294 (C4 (Web Text))
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5269. Min Range: -1.5269
Max Act: 1.2192. Min Act: -0.0001
Data Index: 262234 (C4 (Web Text))
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5269. Min Range: -1.5269
Max Act: 1.1551. Min Act: -0.0001
Data Index: 950288 (C4 (Web Text))
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5269. Min Range: -1.5269
Max Act: 1.2832. Min Act: -0.0001
Data Index: 1188570 (C4 (Web Text))
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5269. Min Range: -1.5269
Max Act: 1.2782. Min Act: -0.0001
Data Index: 901353 (C4 (Web Text))
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5269. Min Range: -1.5269
Max Act: 1.1335. Min Act: -0.0001
Data Index: 1274710 (C4 (Web Text))
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5269. Min Range: -1.5269
Max Act: 1.1266. Min Act: -0.0001
Data Index: 178050 (C4 (Web Text))
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5269. Min Range: -1.5269
Max Act: 1.1255. Min Act: -0.0001
Data Index: 807455 (C4 (Web Text))
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5269. Min Range: -1.5269
Max Act: 1.1417. Min Act: -0.0001
Data Index: 765633 (C4 (Web Text))
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #19