Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4525 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.0155. Min Range: -2.0155
Max Act: 2.0155. Min Act: -0.0001
Data Index: 511408 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0155. Min Range: -2.0155
Max Act: 1.8729. Min Act: -0.0001
Data Index: 838662 (C4 (Web Text))
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0155. Min Range: -2.0155
Max Act: 1.8129. Min Act: -0.0001
Data Index: 1609158 (Python Code)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0155. Min Range: -2.0155
Max Act: 1.8144. Min Act: -0.0001
Data Index: 1555636 (Python Code)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0155. Min Range: -2.0155
Max Act: 1.7018. Min Act: -0.0001
Data Index: 144555 (C4 (Web Text))
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0155. Min Range: -2.0155
Max Act: 1.7217. Min Act: -0.0001
Data Index: 1612484 (Python Code)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0155. Min Range: -2.0155
Max Act: 1.4651. Min Act: -0.0001
Data Index: 624040 (C4 (Web Text))
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0155. Min Range: -2.0155
Max Act: 1.3709. Min Act: -0.0001
Data Index: 1623134 (Python Code)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0155. Min Range: -2.0155
Max Act: 1.6883. Min Act: -0.0001
Data Index: 470855 (C4 (Web Text))
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0155. Min Range: -2.0155
Max Act: 1.4991. Min Act: -0.0001
Data Index: 1517635 (Python Code)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0155. Min Range: -2.0155
Max Act: 1.5634. Min Act: -0.0001
Data Index: 387380 (C4 (Web Text))
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0155. Min Range: -2.0155
Max Act: 1.7145. Min Act: -0.0001
Data Index: 1625191 (Python Code)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0155. Min Range: -2.0155
Max Act: 1.7776. Min Act: -0.0001
Data Index: 904742 (C4 (Web Text))
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0155. Min Range: -2.0155
Max Act: 1.5653. Min Act: -0.0001
Data Index: 1445272 (Python Code)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0155. Min Range: -2.0155
Max Act: 1.4332. Min Act: -0.0001
Data Index: 1310839 (C4 (Web Text))
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0155. Min Range: -2.0155
Max Act: 1.3225. Min Act: -0.0001
Data Index: 1485762 (Python Code)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0155. Min Range: -2.0155
Max Act: 1.1005. Min Act: -0.0001
Data Index: 438507 (C4 (Web Text))
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0155. Min Range: -2.0155
Max Act: 1.3943. Min Act: -0.0001
Data Index: 1410524 (Python Code)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0155. Min Range: -2.0155
Max Act: 1.6304. Min Act: -0.0001
Data Index: 1393502 (Python Code)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0155. Min Range: -2.0155
Max Act: 1.4334. Min Act: -0.0001
Data Index: 1013609 (C4 (Web Text))
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #19