Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3721 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.3634. Min Range: -0.3634
Max Act: 0.3634. Min Act: -0.0001
Data Index: 800450 (C4 (Web Text))
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.3634. Min Range: -0.3634
Max Act: 0.2933. Min Act: -0.0001
Data Index: 558838 (C4 (Web Text))
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.3634. Min Range: -0.3634
Max Act: 0.2817. Min Act: -0.0001
Data Index: 312888 (C4 (Web Text))
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.3634. Min Range: -0.3634
Max Act: 0.3016. Min Act: -0.0001
Data Index: 1026492 (C4 (Web Text))
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.3634. Min Range: -0.3634
Max Act: 0.2800. Min Act: -0.0001
Data Index: 137462 (C4 (Web Text))
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.3634. Min Range: -0.3634
Max Act: 0.2798. Min Act: -0.0001
Data Index: 1299335 (C4 (Web Text))
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.3634. Min Range: -0.3634
Max Act: 0.2780. Min Act: -0.0001
Data Index: 276675 (C4 (Web Text))
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.3634. Min Range: -0.3634
Max Act: 0.2556. Min Act: -0.0001
Data Index: 130251 (C4 (Web Text))
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.3634. Min Range: -0.3634
Max Act: 0.2616. Min Act: -0.0001
Data Index: 198399 (C4 (Web Text))
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.3634. Min Range: -0.3634
Max Act: 0.2565. Min Act: -0.0001
Data Index: 814199 (C4 (Web Text))
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.3634. Min Range: -0.3634
Max Act: 0.2600. Min Act: -0.0001
Data Index: 1259142 (C4 (Web Text))
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.3634. Min Range: -0.3634
Max Act: 0.2592. Min Act: -0.0001
Data Index: 290153 (C4 (Web Text))
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.3634. Min Range: -0.3634
Max Act: 0.2364. Min Act: -0.0001
Data Index: 138653 (C4 (Web Text))
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.3634. Min Range: -0.3634
Max Act: 0.2690. Min Act: -0.0001
Data Index: 925678 (C4 (Web Text))
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.3634. Min Range: -0.3634
Max Act: 0.2573. Min Act: -0.0001
Data Index: 881139 (C4 (Web Text))
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.3634. Min Range: -0.3634
Max Act: 0.2584. Min Act: -0.0001
Data Index: 1027114 (C4 (Web Text))
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.3634. Min Range: -0.3634
Max Act: 0.2659. Min Act: -0.0001
Data Index: 380403 (C4 (Web Text))
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.3634. Min Range: -0.3634
Max Act: 0.2480. Min Act: -0.0001
Data Index: 810859 (C4 (Web Text))
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.3634. Min Range: -0.3634
Max Act: 0.2386. Min Act: -0.0001
Data Index: 475887 (C4 (Web Text))
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.3634. Min Range: -0.3634
Max Act: 0.2454. Min Act: -0.0001
Data Index: 585792 (C4 (Web Text))
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #19