Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4563 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.0373. Min Range: -2.0373
Max Act: 1.9874. Min Act: -0.0001
Data Index: 276745 (C4 (Web Text))
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0373. Min Range: -2.0373
Max Act: 2.0373. Min Act: -0.0001
Data Index: 1527948 (Python Code)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0373. Min Range: -2.0373
Max Act: 1.9982. Min Act: -0.0001
Data Index: 950599 (C4 (Web Text))
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0373. Min Range: -2.0373
Max Act: 1.9535. Min Act: -0.0001
Data Index: 1479327 (Python Code)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0373. Min Range: -2.0373
Max Act: 1.7809. Min Act: -0.0001
Data Index: 288998 (C4 (Web Text))
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0373. Min Range: -2.0373
Max Act: 1.7251. Min Act: -0.0001
Data Index: 779173 (C4 (Web Text))
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0373. Min Range: -2.0373
Max Act: 1.4387. Min Act: -0.0001
Data Index: 1421923 (Python Code)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0373. Min Range: -2.0373
Max Act: 1.7641. Min Act: -0.0001
Data Index: 1110383 (C4 (Web Text))
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0373. Min Range: -2.0373
Max Act: 1.7223. Min Act: -0.0001
Data Index: 334024 (C4 (Web Text))
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0373. Min Range: -2.0373
Max Act: 1.6830. Min Act: -0.0001
Data Index: 942265 (C4 (Web Text))
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0373. Min Range: -2.0373
Max Act: 1.7573. Min Act: -0.0001
Data Index: 1101708 (C4 (Web Text))
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0373. Min Range: -2.0373
Max Act: 1.7281. Min Act: -0.0001
Data Index: 201199 (C4 (Web Text))
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0373. Min Range: -2.0373
Max Act: 1.9152. Min Act: -0.0001
Data Index: 1252847 (C4 (Web Text))
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0373. Min Range: -2.0373
Max Act: 1.5973. Min Act: -0.0001
Data Index: 798885 (C4 (Web Text))
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0373. Min Range: -2.0373
Max Act: 1.5800. Min Act: -0.0001
Data Index: 874298 (C4 (Web Text))
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0373. Min Range: -2.0373
Max Act: 1.6806. Min Act: -0.0001
Data Index: 428467 (C4 (Web Text))
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0373. Min Range: -2.0373
Max Act: 1.4878. Min Act: -0.0001
Data Index: 880042 (C4 (Web Text))
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0373. Min Range: -2.0373
Max Act: 1.5551. Min Act: -0.0001
Data Index: 547664 (C4 (Web Text))
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0373. Min Range: -2.0373
Max Act: 1.7429. Min Act: -0.0001
Data Index: 1516686 (Python Code)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0373. Min Range: -2.0373
Max Act: 1.5389. Min Act: -0.0001
Data Index: 301721 (C4 (Web Text))
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #19