Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3930 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 3.1436. Min Range: -3.1436
Max Act: 3.1436. Min Act: -0.0001
Data Index: 1497086 (Python Code)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1436. Min Range: -3.1436
Max Act: 2.2360. Min Act: -0.0001
Data Index: 959009 (C4 (Web Text))
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1436. Min Range: -3.1436
Max Act: 2.3679. Min Act: -0.0001
Data Index: 1223858 (C4 (Web Text))
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1436. Min Range: -3.1436
Max Act: 2.3768. Min Act: -0.0001
Data Index: 1266193 (C4 (Web Text))
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1436. Min Range: -3.1436
Max Act: 2.2009. Min Act: -0.0001
Data Index: 70833 (C4 (Web Text))
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1436. Min Range: -3.1436
Max Act: 2.3639. Min Act: -0.0001
Data Index: 316940 (C4 (Web Text))
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1436. Min Range: -3.1436
Max Act: 2.1558. Min Act: -0.0001
Data Index: 1168721 (C4 (Web Text))
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1436. Min Range: -3.1436
Max Act: 2.2446. Min Act: -0.0001
Data Index: 1269130 (C4 (Web Text))
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1436. Min Range: -3.1436
Max Act: 2.4324. Min Act: -0.0001
Data Index: 388843 (C4 (Web Text))
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1436. Min Range: -3.1436
Max Act: 2.0160. Min Act: -0.0001
Data Index: 1328893 (C4 (Web Text))
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1436. Min Range: -3.1436
Max Act: 2.1125. Min Act: -0.0001
Data Index: 1381097 (Python Code)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1436. Min Range: -3.1436
Max Act: 2.0798. Min Act: -0.0001
Data Index: 397639 (C4 (Web Text))
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1436. Min Range: -3.1436
Max Act: 2.1859. Min Act: -0.0001
Data Index: 341025 (C4 (Web Text))
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1436. Min Range: -3.1436
Max Act: 1.8725. Min Act: -0.0001
Data Index: 1142996 (C4 (Web Text))
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1436. Min Range: -3.1436
Max Act: 2.0477. Min Act: -0.0001
Data Index: 1189937 (C4 (Web Text))
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1436. Min Range: -3.1436
Max Act: 1.8352. Min Act: -0.0001
Data Index: 51040 (C4 (Web Text))
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1436. Min Range: -3.1436
Max Act: 2.1257. Min Act: -0.0001
Data Index: 181551 (C4 (Web Text))
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1436. Min Range: -3.1436
Max Act: 1.9540. Min Act: -0.0001
Data Index: 432976 (C4 (Web Text))
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1436. Min Range: -3.1436
Max Act: 1.9060. Min Act: -0.0001
Data Index: 410320 (C4 (Web Text))
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1436. Min Range: -3.1436
Max Act: 1.8930. Min Act: -0.0001
Data Index: 1531616 (Python Code)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19