Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3689 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.7956. Min Range: -1.7956

Max Act: 1.7956. Min Act: -0.0000

Data Index: 1342894 (The Pile)

Max Activating Token Index: 279

Text #1

Max Range: 1.7956. Min Range: -1.7956

Max Act: 1.6959. Min Act: -0.0000

Data Index: 238843 (The Pile)

Max Activating Token Index: 60

Text #2

Max Range: 1.7956. Min Range: -1.7956

Max Act: 1.6251. Min Act: -0.0000

Data Index: 425094 (The Pile)

Max Activating Token Index: 876

Text #3

Max Range: 1.7956. Min Range: -1.7956

Max Act: 1.6460. Min Act: -0.0000

Data Index: 189925 (The Pile)

Max Activating Token Index: 916

Text #4

Max Range: 1.7956. Min Range: -1.7956

Max Act: 1.5328. Min Act: -0.0000

Data Index: 697896 (The Pile)

Max Activating Token Index: 138

Text #5

Max Range: 1.7956. Min Range: -1.7956

Max Act: 1.6454. Min Act: -0.0000

Data Index: 1382072 (The Pile)

Max Activating Token Index: 83

Text #6

Max Range: 1.7956. Min Range: -1.7956

Max Act: 1.4353. Min Act: -0.0000

Data Index: 1134422 (The Pile)

Max Activating Token Index: 754

Text #7

Max Range: 1.7956. Min Range: -1.7956

Max Act: 1.4004. Min Act: -0.0000

Data Index: 338042 (The Pile)

Max Activating Token Index: 957

Text #8

Max Range: 1.7956. Min Range: -1.7956

Max Act: 1.5177. Min Act: -0.0000

Data Index: 637278 (The Pile)

Max Activating Token Index: 465

Text #9

Max Range: 1.7956. Min Range: -1.7956

Max Act: 1.4661. Min Act: -0.0000

Data Index: 188220 (The Pile)

Max Activating Token Index: 355

Text #10

Max Range: 1.7956. Min Range: -1.7956

Max Act: 1.6369. Min Act: -0.0000

Data Index: 1728524 (The Pile)

Max Activating Token Index: 407

Text #11

Max Range: 1.7956. Min Range: -1.7956

Max Act: 1.5312. Min Act: -0.0000

Data Index: 1987431 (The Pile)

Max Activating Token Index: 599

Text #12

Max Range: 1.7956. Min Range: -1.7956

Max Act: 1.4102. Min Act: -0.0000

Data Index: 1566648 (The Pile)

Max Activating Token Index: 359

Text #13

Max Range: 1.7956. Min Range: -1.7956

Max Act: 1.4517. Min Act: -0.0000

Data Index: 1187341 (The Pile)

Max Activating Token Index: 769

Text #14

Max Range: 1.7956. Min Range: -1.7956

Max Act: 1.4462. Min Act: -0.0000

Data Index: 66759 (The Pile)

Max Activating Token Index: 269

Text #15

Max Range: 1.7956. Min Range: -1.7956

Max Act: 1.4450. Min Act: -0.0000

Data Index: 1726769 (The Pile)

Max Activating Token Index: 449

Text #16

Max Range: 1.7956. Min Range: -1.7956

Max Act: 1.3367. Min Act: -0.0000

Data Index: 522094 (The Pile)

Max Activating Token Index: 774

Text #17

Max Range: 1.7956. Min Range: -1.7956

Max Act: 1.4746. Min Act: -0.0000

Data Index: 1546993 (The Pile)

Max Activating Token Index: 456

Text #18

Max Range: 1.7956. Min Range: -1.7956

Max Act: 1.5784. Min Act: -0.0000

Data Index: 1661684 (The Pile)

Max Activating Token Index: 53

Text #19

Max Range: 1.7956. Min Range: -1.7956

Max Act: 1.4089. Min Act: -0.0000

Data Index: 359785 (The Pile)

Max Activating Token Index: 242