Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 816 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')
Text #0
Max Range: 0.3158. Min Range: -0.3158
Max Act: 0.3158. Min Act: -0.0001
Data Index: 1155235 (C4 (Web Text))
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.3158. Min Range: -0.3158
Max Act: 0.2757. Min Act: -0.0001
Data Index: 431083 (C4 (Web Text))
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.3158. Min Range: -0.3158
Max Act: 0.3115. Min Act: -0.0001
Data Index: 618586 (C4 (Web Text))
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.3158. Min Range: -0.3158
Max Act: 0.2942. Min Act: -0.0001
Data Index: 624458 (C4 (Web Text))
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.3158. Min Range: -0.3158
Max Act: 0.2906. Min Act: -0.0001
Data Index: 439645 (C4 (Web Text))
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.3158. Min Range: -0.3158
Max Act: 0.2777. Min Act: -0.0001
Data Index: 195306 (C4 (Web Text))
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.3158. Min Range: -0.3158
Max Act: 0.2615. Min Act: -0.0001
Data Index: 705341 (C4 (Web Text))
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.3158. Min Range: -0.3158
Max Act: 0.2852. Min Act: -0.0001
Data Index: 1291621 (C4 (Web Text))
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.3158. Min Range: -0.3158
Max Act: 0.2759. Min Act: -0.0001
Data Index: 483753 (C4 (Web Text))
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.3158. Min Range: -0.3158
Max Act: 0.2682. Min Act: -0.0001
Data Index: 852059 (C4 (Web Text))
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.3158. Min Range: -0.3158
Max Act: 0.2573. Min Act: -0.0001
Data Index: 1217012 (C4 (Web Text))
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.3158. Min Range: -0.3158
Max Act: 0.2598. Min Act: -0.0001
Data Index: 736043 (C4 (Web Text))
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.3158. Min Range: -0.3158
Max Act: 0.2500. Min Act: -0.0001
Data Index: 391140 (C4 (Web Text))
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.3158. Min Range: -0.3158
Max Act: 0.2661. Min Act: -0.0001
Data Index: 1185507 (C4 (Web Text))
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.3158. Min Range: -0.3158
Max Act: 0.2587. Min Act: -0.0001
Data Index: 936059 (C4 (Web Text))
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.3158. Min Range: -0.3158
Max Act: 0.2459. Min Act: -0.0001
Data Index: 397788 (C4 (Web Text))
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.3158. Min Range: -0.3158
Max Act: 0.2428. Min Act: -0.0001
Data Index: 208432 (C4 (Web Text))
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.3158. Min Range: -0.3158
Max Act: 0.2413. Min Act: -0.0001
Data Index: 504923 (C4 (Web Text))
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.3158. Min Range: -0.3158
Max Act: 0.2492. Min Act: -0.0001
Data Index: 746224 (C4 (Web Text))
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.3158. Min Range: -0.3158
Max Act: 0.2377. Min Act: -0.0001
Data Index: 752962 (C4 (Web Text))
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #19