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

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

Neuron 4512 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: 2.1774. Min Range: -2.1774

Max Act: 2.1774. Min Act: -0.0000

Data Index: 1250256 (C4 (Web Text))

Max Activating Token Index: 247

Text #1

Max Range: 2.1774. Min Range: -2.1774

Max Act: 2.0131. Min Act: -0.0000

Data Index: 1101570 (C4 (Web Text))

Max Activating Token Index: 862

Text #2

Max Range: 2.1774. Min Range: -2.1774

Max Act: 2.1154. Min Act: -0.0000

Data Index: 992569 (C4 (Web Text))

Max Activating Token Index: 267

Text #3

Max Range: 2.1774. Min Range: -2.1774

Max Act: 1.9033. Min Act: -0.0000

Data Index: 659555 (C4 (Web Text))

Max Activating Token Index: 567

Text #4

Max Range: 2.1774. Min Range: -2.1774

Max Act: 1.9876. Min Act: -0.0000

Data Index: 757331 (C4 (Web Text))

Max Activating Token Index: 432

Text #5

Max Range: 2.1774. Min Range: -2.1774

Max Act: 1.9719. Min Act: -0.0000

Data Index: 1015124 (C4 (Web Text))

Max Activating Token Index: 378

Text #6

Max Range: 2.1774. Min Range: -2.1774

Max Act: 2.0694. Min Act: -0.0000

Data Index: 1136128 (C4 (Web Text))

Max Activating Token Index: 868

Text #7

Max Range: 2.1774. Min Range: -2.1774

Max Act: 1.9568. Min Act: -0.0000

Data Index: 695786 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 2.1774. Min Range: -2.1774

Max Act: 1.9442. Min Act: -0.0000

Data Index: 1271473 (C4 (Web Text))

Max Activating Token Index: 955

Text #9

Max Range: 2.1774. Min Range: -2.1774

Max Act: 1.8796. Min Act: -0.0000

Data Index: 619261 (C4 (Web Text))

Max Activating Token Index: 87

Text #10

Max Range: 2.1774. Min Range: -2.1774

Max Act: 1.6888. Min Act: -0.0000

Data Index: 247587 (C4 (Web Text))

Max Activating Token Index: 881

Text #11

Max Range: 2.1774. Min Range: -2.1774

Max Act: 1.8615. Min Act: -0.0000

Data Index: 879619 (C4 (Web Text))

Max Activating Token Index: 505

Text #12

Max Range: 2.1774. Min Range: -2.1774

Max Act: 1.8272. Min Act: -0.0000

Data Index: 257646 (C4 (Web Text))

Max Activating Token Index: 592

Text #13

Max Range: 2.1774. Min Range: -2.1774

Max Act: 1.8773. Min Act: -0.0000

Data Index: 70780 (C4 (Web Text))

Max Activating Token Index: 202

Text #14

Max Range: 2.1774. Min Range: -2.1774

Max Act: 1.7638. Min Act: -0.0000

Data Index: 610714 (C4 (Web Text))

Max Activating Token Index: 770

Text #15

Max Range: 2.1774. Min Range: -2.1774

Max Act: 1.7452. Min Act: -0.0000

Data Index: 792484 (C4 (Web Text))

Max Activating Token Index: 52

Text #16

Max Range: 2.1774. Min Range: -2.1774

Max Act: 1.7991. Min Act: -0.0000

Data Index: 1194304 (C4 (Web Text))

Max Activating Token Index: 813

Text #17

Max Range: 2.1774. Min Range: -2.1774

Max Act: 1.6782. Min Act: -0.0000

Data Index: 1112104 (C4 (Web Text))

Max Activating Token Index: 495

Text #18

Max Range: 2.1774. Min Range: -2.1774

Max Act: 1.6887. Min Act: -0.0000

Data Index: 332626 (C4 (Web Text))

Max Activating Token Index: 69

Text #19

Max Range: 2.1774. Min Range: -2.1774

Max Act: 1.5940. Min Act: -0.0000

Data Index: 1345152 (C4 (Web Text))

Max Activating Token Index: 197