Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2438 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 3.0781. Min Range: -3.0781
Max Act: 3.0781. Min Act: -0.0001
Data Index: 1239194 (C4 (Web Text))
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0781. Min Range: -3.0781
Max Act: 2.6052. Min Act: -0.0001
Data Index: 1231191 (C4 (Web Text))
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0781. Min Range: -3.0781
Max Act: 2.5360. Min Act: -0.0001
Data Index: 1231394 (C4 (Web Text))
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0781. Min Range: -3.0781
Max Act: 2.5248. Min Act: -0.0001
Data Index: 205896 (C4 (Web Text))
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0781. Min Range: -3.0781
Max Act: 2.5943. Min Act: -0.0001
Data Index: 530198 (C4 (Web Text))
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0781. Min Range: -3.0781
Max Act: 2.5496. Min Act: -0.0001
Data Index: 387234 (C4 (Web Text))
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0781. Min Range: -3.0781
Max Act: 2.5372. Min Act: -0.0001
Data Index: 134983 (C4 (Web Text))
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0781. Min Range: -3.0781
Max Act: 2.3622. Min Act: -0.0001
Data Index: 906566 (C4 (Web Text))
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0781. Min Range: -3.0781
Max Act: 2.4505. Min Act: -0.0001
Data Index: 294487 (C4 (Web Text))
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0781. Min Range: -3.0781
Max Act: 2.2309. Min Act: -0.0001
Data Index: 37746 (C4 (Web Text))
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0781. Min Range: -3.0781
Max Act: 2.0781. Min Act: -0.0001
Data Index: 414826 (C4 (Web Text))
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0781. Min Range: -3.0781
Max Act: 2.1211. Min Act: -0.0001
Data Index: 652974 (C4 (Web Text))
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0781. Min Range: -3.0781
Max Act: 2.3807. Min Act: -0.0001
Data Index: 620233 (C4 (Web Text))
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0781. Min Range: -3.0781
Max Act: 1.9626. Min Act: -0.0001
Data Index: 494619 (C4 (Web Text))
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0781. Min Range: -3.0781
Max Act: 2.0026. Min Act: -0.0001
Data Index: 1305240 (C4 (Web Text))
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0781. Min Range: -3.0781
Max Act: 2.0274. Min Act: -0.0001
Data Index: 623452 (C4 (Web Text))
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0781. Min Range: -3.0781
Max Act: 1.9801. Min Act: -0.0001
Data Index: 152626 (C4 (Web Text))
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0781. Min Range: -3.0781
Max Act: 1.8633. Min Act: -0.0001
Data Index: 10332 (C4 (Web Text))
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0781. Min Range: -3.0781
Max Act: 1.9841. Min Act: -0.0001
Data Index: 382301 (C4 (Web Text))
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0781. Min Range: -3.0781
Max Act: 2.0957. Min Act: -0.0001
Data Index: 1069879 (C4 (Web Text))
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19