Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1945 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.3944. Min Range: -4.3944

Max Act: 4.3944. Min Act: -0.0000

Data Index: 359307 (C4 (Web Text))

Max Activating Token Index: 219

Text #1

Max Range: 4.3944. Min Range: -4.3944

Max Act: 4.2648. Min Act: -0.0000

Data Index: 236164 (C4 (Web Text))

Max Activating Token Index: 253

Text #2

Max Range: 4.3944. Min Range: -4.3944

Max Act: 3.6535. Min Act: -0.0000

Data Index: 535282 (C4 (Web Text))

Max Activating Token Index: 973

Text #3

Max Range: 4.3944. Min Range: -4.3944

Max Act: 3.5869. Min Act: -0.0000

Data Index: 1248087 (C4 (Web Text))

Max Activating Token Index: 891

Text #4

Max Range: 4.3944. Min Range: -4.3944

Max Act: 3.5368. Min Act: -0.0000

Data Index: 462428 (C4 (Web Text))

Max Activating Token Index: 935

Text #5

Max Range: 4.3944. Min Range: -4.3944

Max Act: 3.5503. Min Act: -0.0000

Data Index: 995514 (C4 (Web Text))

Max Activating Token Index: 53

Text #6

Max Range: 4.3944. Min Range: -4.3944

Max Act: 3.4770. Min Act: -0.0000

Data Index: 294840 (C4 (Web Text))

Max Activating Token Index: 225

Text #7

Max Range: 4.3944. Min Range: -4.3944

Max Act: 3.6016. Min Act: -0.0000

Data Index: 852863 (C4 (Web Text))

Max Activating Token Index: 56

Text #8

Max Range: 4.3944. Min Range: -4.3944

Max Act: 3.0776. Min Act: -0.0000

Data Index: 1473141 (Python Code)

Max Activating Token Index: 816

Text #9

Max Range: 4.3944. Min Range: -4.3944

Max Act: 3.2328. Min Act: -0.0000

Data Index: 856933 (C4 (Web Text))

Max Activating Token Index: 195

Text #10

Max Range: 4.3944. Min Range: -4.3944

Max Act: 3.2754. Min Act: -0.0000

Data Index: 661239 (C4 (Web Text))

Max Activating Token Index: 804

Text #11

Max Range: 4.3944. Min Range: -4.3944

Max Act: 3.2853. Min Act: -0.0000

Data Index: 530941 (C4 (Web Text))

Max Activating Token Index: 264

Text #12

Max Range: 4.3944. Min Range: -4.3944

Max Act: 3.2044. Min Act: -0.0000

Data Index: 441690 (C4 (Web Text))

Max Activating Token Index: 808

Text #13

Max Range: 4.3944. Min Range: -4.3944

Max Act: 3.0547. Min Act: -0.0000

Data Index: 1259980 (C4 (Web Text))

Max Activating Token Index: 99

Text #14

Max Range: 4.3944. Min Range: -4.3944

Max Act: 3.1986. Min Act: -0.0000

Data Index: 10645 (C4 (Web Text))

Max Activating Token Index: 268

Text #15

Max Range: 4.3944. Min Range: -4.3944

Max Act: 2.9485. Min Act: -0.0000

Data Index: 1036555 (C4 (Web Text))

Max Activating Token Index: 68

Text #16

Max Range: 4.3944. Min Range: -4.3944

Max Act: 3.1726. Min Act: -0.0000

Data Index: 653754 (C4 (Web Text))

Max Activating Token Index: 395

Text #17

Max Range: 4.3944. Min Range: -4.3944

Max Act: 3.0979. Min Act: -0.0000

Data Index: 637405 (C4 (Web Text))

Max Activating Token Index: 613

Text #18

Max Range: 4.3944. Min Range: -4.3944

Max Act: 2.9689. Min Act: -0.0000

Data Index: 1164545 (C4 (Web Text))

Max Activating Token Index: 43

Text #19

Max Range: 4.3944. Min Range: -4.3944

Max Act: 3.2512. Min Act: -0.0000

Data Index: 713375 (C4 (Web Text))

Max Activating Token Index: 708