Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3832 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.8554. Min Range: -1.8554
Max Act: 1.8554. Min Act: -0.0001
Data Index: 963672 (C4 (Web Text))
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8554. Min Range: -1.8554
Max Act: 1.7197. Min Act: -0.0001
Data Index: 666568 (C4 (Web Text))
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8554. Min Range: -1.8554
Max Act: 1.7449. Min Act: -0.0001
Data Index: 1029033 (C4 (Web Text))
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8554. Min Range: -1.8554
Max Act: 1.7279. Min Act: -0.0001
Data Index: 782340 (C4 (Web Text))
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8554. Min Range: -1.8554
Max Act: 1.7355. Min Act: -0.0001
Data Index: 177787 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8554. Min Range: -1.8554
Max Act: 1.7468. Min Act: -0.0001
Data Index: 513831 (C4 (Web Text))
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8554. Min Range: -1.8554
Max Act: 1.7645. Min Act: -0.0001
Data Index: 1031900 (C4 (Web Text))
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8554. Min Range: -1.8554
Max Act: 1.7383. Min Act: -0.0001
Data Index: 95451 (C4 (Web Text))
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8554. Min Range: -1.8554
Max Act: 1.6980. Min Act: -0.0001
Data Index: 836988 (C4 (Web Text))
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8554. Min Range: -1.8554
Max Act: 1.6885. Min Act: -0.0001
Data Index: 187974 (C4 (Web Text))
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8554. Min Range: -1.8554
Max Act: 1.6784. Min Act: -0.0001
Data Index: 1168920 (C4 (Web Text))
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8554. Min Range: -1.8554
Max Act: 1.7055. Min Act: -0.0001
Data Index: 1083426 (C4 (Web Text))
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8554. Min Range: -1.8554
Max Act: 1.7014. Min Act: -0.0001
Data Index: 1058505 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8554. Min Range: -1.8554
Max Act: 1.4704. Min Act: -0.0001
Data Index: 1461359 (Python Code)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8554. Min Range: -1.8554
Max Act: 1.5930. Min Act: -0.0001
Data Index: 1352328 (C4 (Web Text))
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8554. Min Range: -1.8554
Max Act: 1.6254. Min Act: -0.0001
Data Index: 1469126 (Python Code)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8554. Min Range: -1.8554
Max Act: 1.6769. Min Act: -0.0001
Data Index: 314500 (C4 (Web Text))
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8554. Min Range: -1.8554
Max Act: 1.6308. Min Act: -0.0001
Data Index: 438876 (C4 (Web Text))
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8554. Min Range: -1.8554
Max Act: 1.4850. Min Act: -0.0001
Data Index: 375267 (C4 (Web Text))
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8554. Min Range: -1.8554
Max Act: 1.5327. Min Act: -0.0001
Data Index: 1199039 (C4 (Web Text))
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #19