Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4427 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 5.0912. Min Range: -5.0912
Max Act: 5.0912. Min Act: -0.0001
Data Index: 1569794 (Python Code)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0912. Min Range: -5.0912
Max Act: 4.5777. Min Act: -0.0001
Data Index: 1417857 (Python Code)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0912. Min Range: -5.0912
Max Act: 4.3437. Min Act: -0.0001
Data Index: 1496450 (Python Code)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0912. Min Range: -5.0912
Max Act: 4.4350. Min Act: -0.0001
Data Index: 1453268 (Python Code)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0912. Min Range: -5.0912
Max Act: 4.1448. Min Act: -0.0001
Data Index: 1447426 (Python Code)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0912. Min Range: -5.0912
Max Act: 4.0335. Min Act: -0.0001
Data Index: 1497540 (Python Code)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0912. Min Range: -5.0912
Max Act: 4.1781. Min Act: -0.0001
Data Index: 1553952 (Python Code)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0912. Min Range: -5.0912
Max Act: 4.0072. Min Act: -0.0001
Data Index: 1586253 (Python Code)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0912. Min Range: -5.0912
Max Act: 4.1209. Min Act: -0.0001
Data Index: 1494879 (Python Code)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0912. Min Range: -5.0912
Max Act: 3.9332. Min Act: -0.0001
Data Index: 1527855 (Python Code)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0912. Min Range: -5.0912
Max Act: 3.7742. Min Act: -0.0001
Data Index: 1404374 (Python Code)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0912. Min Range: -5.0912
Max Act: 3.7649. Min Act: -0.0001
Data Index: 1456397 (Python Code)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0912. Min Range: -5.0912
Max Act: 4.0413. Min Act: -0.0001
Data Index: 1518501 (Python Code)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0912. Min Range: -5.0912
Max Act: 4.2201. Min Act: -0.0001
Data Index: 1503990 (Python Code)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0912. Min Range: -5.0912
Max Act: 3.8694. Min Act: -0.0001
Data Index: 1386346 (Python Code)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0912. Min Range: -5.0912
Max Act: 3.7141. Min Act: -0.0001
Data Index: 1423728 (Python Code)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0912. Min Range: -5.0912
Max Act: 4.0112. Min Act: -0.0001
Data Index: 1427408 (Python Code)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0912. Min Range: -5.0912
Max Act: 3.7095. Min Act: -0.0001
Data Index: 1573460 (Python Code)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0912. Min Range: -5.0912
Max Act: 3.9991. Min Act: -0.0001
Data Index: 1642722 (Python Code)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0912. Min Range: -5.0912
Max Act: 3.7937. Min Act: -0.0001
Data Index: 1641239 (Python Code)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #19