Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2334 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.6708. Min Range: -2.6708
Max Act: 2.6648. Min Act: -0.0001
Data Index: 308387 (C4 (Web Text))
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6708. Min Range: -2.6708
Max Act: 2.6708. Min Act: -0.0001
Data Index: 1001530 (C4 (Web Text))
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6708. Min Range: -2.6708
Max Act: 2.2937. Min Act: -0.0001
Data Index: 437725 (C4 (Web Text))
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6708. Min Range: -2.6708
Max Act: 2.2285. Min Act: -0.0001
Data Index: 1563976 (Python Code)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6708. Min Range: -2.6708
Max Act: 1.8091. Min Act: -0.0001
Data Index: 382942 (C4 (Web Text))
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6708. Min Range: -2.6708
Max Act: 2.0978. Min Act: -0.0001
Data Index: 1214903 (C4 (Web Text))
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6708. Min Range: -2.6708
Max Act: 2.2591. Min Act: -0.0001
Data Index: 1264714 (C4 (Web Text))
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6708. Min Range: -2.6708
Max Act: 2.1078. Min Act: -0.0001
Data Index: 897471 (C4 (Web Text))
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6708. Min Range: -2.6708
Max Act: 2.1921. Min Act: -0.0001
Data Index: 708128 (C4 (Web Text))
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6708. Min Range: -2.6708
Max Act: 2.2485. Min Act: -0.0001
Data Index: 436617 (C4 (Web Text))
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6708. Min Range: -2.6708
Max Act: 2.2365. Min Act: -0.0001
Data Index: 297668 (C4 (Web Text))
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6708. Min Range: -2.6708
Max Act: 1.9930. Min Act: -0.0001
Data Index: 39581 (C4 (Web Text))
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6708. Min Range: -2.6708
Max Act: 1.9266. Min Act: -0.0001
Data Index: 63019 (C4 (Web Text))
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6708. Min Range: -2.6708
Max Act: 1.9670. Min Act: -0.0001
Data Index: 792086 (C4 (Web Text))
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6708. Min Range: -2.6708
Max Act: 2.0595. Min Act: -0.0001
Data Index: 821000 (C4 (Web Text))
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6708. Min Range: -2.6708
Max Act: 2.0208. Min Act: -0.0001
Data Index: 172937 (C4 (Web Text))
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6708. Min Range: -2.6708
Max Act: 1.7807. Min Act: -0.0001
Data Index: 548497 (C4 (Web Text))
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6708. Min Range: -2.6708
Max Act: 1.6793. Min Act: -0.0001
Data Index: 558686 (C4 (Web Text))
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6708. Min Range: -2.6708
Max Act: 1.7683. Min Act: -0.0001
Data Index: 105563 (C4 (Web Text))
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6708. Min Range: -2.6708
Max Act: 1.9191. Min Act: -0.0001
Data Index: 660444 (C4 (Web Text))
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #19