Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.9802. Min Range: -0.9802
Max Act: 0.9802. Min Act: -0.0001
Data Index: 855348 (C4 (Web Text))
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9802. Min Range: -0.9802
Max Act: 0.9323. Min Act: -0.0001
Data Index: 383863 (C4 (Web Text))
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9802. Min Range: -0.9802
Max Act: 0.8590. Min Act: -0.0001
Data Index: 361438 (C4 (Web Text))
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9802. Min Range: -0.9802
Max Act: 0.7648. Min Act: -0.0001
Data Index: 152428 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9802. Min Range: -0.9802
Max Act: 0.7908. Min Act: -0.0001
Data Index: 321557 (C4 (Web Text))
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9802. Min Range: -0.9802
Max Act: 0.8441. Min Act: -0.0001
Data Index: 907703 (C4 (Web Text))
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9802. Min Range: -0.9802
Max Act: 0.7491. Min Act: -0.0001
Data Index: 158509 (C4 (Web Text))
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9802. Min Range: -0.9802
Max Act: 0.7463. Min Act: -0.0001
Data Index: 1253741 (C4 (Web Text))
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9802. Min Range: -0.9802
Max Act: 0.7422. Min Act: -0.0001
Data Index: 580025 (C4 (Web Text))
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9802. Min Range: -0.9802
Max Act: 0.7380. Min Act: -0.0001
Data Index: 1225150 (C4 (Web Text))
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9802. Min Range: -0.9802
Max Act: 0.6827. Min Act: -0.0001
Data Index: 770332 (C4 (Web Text))
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9802. Min Range: -0.9802
Max Act: 0.7311. Min Act: -0.0001
Data Index: 704264 (C4 (Web Text))
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9802. Min Range: -0.9802
Max Act: 0.7566. Min Act: -0.0001
Data Index: 474771 (C4 (Web Text))
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9802. Min Range: -0.9802
Max Act: 0.7209. Min Act: -0.0001
Data Index: 1180580 (C4 (Web Text))
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9802. Min Range: -0.9802
Max Act: 0.7105. Min Act: -0.0001
Data Index: 18878 (C4 (Web Text))
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9802. Min Range: -0.9802
Max Act: 0.6988. Min Act: -0.0001
Data Index: 857684 (C4 (Web Text))
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9802. Min Range: -0.9802
Max Act: 0.6959. Min Act: -0.0001
Data Index: 634870 (C4 (Web Text))
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9802. Min Range: -0.9802
Max Act: 0.6791. Min Act: -0.0001
Data Index: 685795 (C4 (Web Text))
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9802. Min Range: -0.9802
Max Act: 0.6962. Min Act: -0.0001
Data Index: 411736 (C4 (Web Text))
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9802. Min Range: -0.9802
Max Act: 0.6985. Min Act: -0.0001
Data Index: 1503580 (Python Code)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #19