Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 513 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.6521. Min Range: -0.6521
Max Act: 0.6521. Min Act: -0.0001
Data Index: 725525 (C4 (Web Text))
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.6521. Min Range: -0.6521
Max Act: 0.5422. Min Act: -0.0001
Data Index: 1204672 (C4 (Web Text))
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.6521. Min Range: -0.6521
Max Act: 0.5336. Min Act: -0.0001
Data Index: 1179012 (C4 (Web Text))
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.6521. Min Range: -0.6521
Max Act: 0.5001. Min Act: -0.0001
Data Index: 787860 (C4 (Web Text))
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.6521. Min Range: -0.6521
Max Act: 0.4969. Min Act: -0.0001
Data Index: 572300 (C4 (Web Text))
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.6521. Min Range: -0.6521
Max Act: 0.4671. Min Act: -0.0001
Data Index: 588693 (C4 (Web Text))
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.6521. Min Range: -0.6521
Max Act: 0.4546. Min Act: -0.0001
Data Index: 1278863 (C4 (Web Text))
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.6521. Min Range: -0.6521
Max Act: 0.4650. Min Act: -0.0001
Data Index: 639737 (C4 (Web Text))
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.6521. Min Range: -0.6521
Max Act: 0.4342. Min Act: -0.0001
Data Index: 1087572 (C4 (Web Text))
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.6521. Min Range: -0.6521
Max Act: 0.4307. Min Act: -0.0001
Data Index: 984670 (C4 (Web Text))
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.6521. Min Range: -0.6521
Max Act: 0.4435. Min Act: -0.0001
Data Index: 653044 (C4 (Web Text))
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.6521. Min Range: -0.6521
Max Act: 0.4265. Min Act: -0.0001
Data Index: 1287868 (C4 (Web Text))
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.6521. Min Range: -0.6521
Max Act: 0.4241. Min Act: -0.0001
Data Index: 1104520 (C4 (Web Text))
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.6521. Min Range: -0.6521
Max Act: 0.4350. Min Act: -0.0001
Data Index: 868043 (C4 (Web Text))
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.6521. Min Range: -0.6521
Max Act: 0.4284. Min Act: -0.0001
Data Index: 241862 (C4 (Web Text))
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.6521. Min Range: -0.6521
Max Act: 0.4259. Min Act: -0.0001
Data Index: 988207 (C4 (Web Text))
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.6521. Min Range: -0.6521
Max Act: 0.4402. Min Act: -0.0001
Data Index: 423037 (C4 (Web Text))
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.6521. Min Range: -0.6521
Max Act: 0.4317. Min Act: -0.0001
Data Index: 704925 (C4 (Web Text))
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.6521. Min Range: -0.6521
Max Act: 0.4028. Min Act: -0.0001
Data Index: 399794 (C4 (Web Text))
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.6521. Min Range: -0.6521
Max Act: 0.4018. Min Act: -0.0001
Data Index: 1071485 (C4 (Web Text))
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #19