Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2632 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.3487. Min Range: -0.3487
Max Act: 0.3487. Min Act: -0.0001
Data Index: 837223 (C4 (Web Text))
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.3487. Min Range: -0.3487
Max Act: 0.3459. Min Act: -0.0001
Data Index: 724774 (C4 (Web Text))
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.3487. Min Range: -0.3487
Max Act: 0.3315. Min Act: -0.0001
Data Index: 1213542 (C4 (Web Text))
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.3487. Min Range: -0.3487
Max Act: 0.2541. Min Act: -0.0001
Data Index: 278512 (C4 (Web Text))
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.3487. Min Range: -0.3487
Max Act: 0.2718. Min Act: -0.0001
Data Index: 934912 (C4 (Web Text))
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.3487. Min Range: -0.3487
Max Act: 0.2639. Min Act: -0.0001
Data Index: 1267602 (C4 (Web Text))
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.3487. Min Range: -0.3487
Max Act: 0.2644. Min Act: -0.0001
Data Index: 429588 (C4 (Web Text))
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.3487. Min Range: -0.3487
Max Act: 0.2536. Min Act: -0.0001
Data Index: 1201787 (C4 (Web Text))
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.3487. Min Range: -0.3487
Max Act: 0.2926. Min Act: -0.0001
Data Index: 47085 (C4 (Web Text))
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.3487. Min Range: -0.3487
Max Act: 0.2467. Min Act: -0.0001
Data Index: 539402 (C4 (Web Text))
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.3487. Min Range: -0.3487
Max Act: 0.2547. Min Act: -0.0001
Data Index: 656456 (C4 (Web Text))
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.3487. Min Range: -0.3487
Max Act: 0.2544. Min Act: -0.0001
Data Index: 178321 (C4 (Web Text))
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.3487. Min Range: -0.3487
Max Act: 0.2764. Min Act: -0.0001
Data Index: 849746 (C4 (Web Text))
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.3487. Min Range: -0.3487
Max Act: 0.2407. Min Act: -0.0001
Data Index: 58379 (C4 (Web Text))
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.3487. Min Range: -0.3487
Max Act: 0.2508. Min Act: -0.0001
Data Index: 862826 (C4 (Web Text))
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.3487. Min Range: -0.3487
Max Act: 0.2311. Min Act: -0.0001
Data Index: 769366 (C4 (Web Text))
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.3487. Min Range: -0.3487
Max Act: 0.2282. Min Act: -0.0001
Data Index: 228415 (C4 (Web Text))
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.3487. Min Range: -0.3487
Max Act: 0.2537. Min Act: -0.0001
Data Index: 669984 (C4 (Web Text))
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.3487. Min Range: -0.3487
Max Act: 0.2339. Min Act: -0.0001
Data Index: 330109 (C4 (Web Text))
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.3487. Min Range: -0.3487
Max Act: 0.2423. Min Act: -0.0001
Data Index: 1009133 (C4 (Web Text))
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #19