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

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

Neuron 1616 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9480. Min Range: -1.9480

Max Act: 1.7744. Min Act: -0.0000

Data Index: 506624 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 1.9480. Min Range: -1.9480

Max Act: 1.9480. Min Act: -0.0000

Data Index: 862840 (C4 (Web Text))

Max Activating Token Index: 66

Text #2

Max Range: 1.9480. Min Range: -1.9480

Max Act: 1.8653. Min Act: -0.0000

Data Index: 433529 (C4 (Web Text))

Max Activating Token Index: 479

Text #3

Max Range: 1.9480. Min Range: -1.9480

Max Act: 1.7450. Min Act: -0.0000

Data Index: 298840 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 1.9480. Min Range: -1.9480

Max Act: 1.7292. Min Act: -0.0000

Data Index: 425459 (C4 (Web Text))

Max Activating Token Index: 46

Text #5

Max Range: 1.9480. Min Range: -1.9480

Max Act: 1.6252. Min Act: -0.0000

Data Index: 544924 (C4 (Web Text))

Max Activating Token Index: 922

Text #6

Max Range: 1.9480. Min Range: -1.9480

Max Act: 1.8176. Min Act: -0.0000

Data Index: 1018937 (C4 (Web Text))

Max Activating Token Index: 229

Text #7

Max Range: 1.9480. Min Range: -1.9480

Max Act: 1.4382. Min Act: -0.0000

Data Index: 300954 (C4 (Web Text))

Max Activating Token Index: 654

Text #8

Max Range: 1.9480. Min Range: -1.9480

Max Act: 1.6744. Min Act: -0.0000

Data Index: 637214 (C4 (Web Text))

Max Activating Token Index: 388

Text #9

Max Range: 1.9480. Min Range: -1.9480

Max Act: 1.5480. Min Act: -0.0000

Data Index: 10938 (C4 (Web Text))

Max Activating Token Index: 21

Text #10

Max Range: 1.9480. Min Range: -1.9480

Max Act: 1.6351. Min Act: -0.0000

Data Index: 409069 (C4 (Web Text))

Max Activating Token Index: 816

Text #11

Max Range: 1.9480. Min Range: -1.9480

Max Act: 1.6020. Min Act: -0.0000

Data Index: 834239 (C4 (Web Text))

Max Activating Token Index: 962

Text #12

Max Range: 1.9480. Min Range: -1.9480

Max Act: 1.4035. Min Act: -0.0000

Data Index: 277765 (C4 (Web Text))

Max Activating Token Index: 317

Text #13

Max Range: 1.9480. Min Range: -1.9480

Max Act: 1.5888. Min Act: -0.0000

Data Index: 840606 (C4 (Web Text))

Max Activating Token Index: 782

Text #14

Max Range: 1.9480. Min Range: -1.9480

Max Act: 1.5671. Min Act: -0.0000

Data Index: 1267187 (C4 (Web Text))

Max Activating Token Index: 95

Text #15

Max Range: 1.9480. Min Range: -1.9480

Max Act: 1.5813. Min Act: -0.0000

Data Index: 1084808 (C4 (Web Text))

Max Activating Token Index: 487

Text #16

Max Range: 1.9480. Min Range: -1.9480

Max Act: 1.4718. Min Act: -0.0000

Data Index: 552040 (C4 (Web Text))

Max Activating Token Index: 55

Text #17

Max Range: 1.9480. Min Range: -1.9480

Max Act: 1.5461. Min Act: -0.0000

Data Index: 412643 (C4 (Web Text))

Max Activating Token Index: 17

Text #18

Max Range: 1.9480. Min Range: -1.9480

Max Act: 1.5378. Min Act: -0.0000

Data Index: 589109 (C4 (Web Text))

Max Activating Token Index: 617

Text #19

Max Range: 1.9480. Min Range: -1.9480

Max Act: 1.6147. Min Act: -0.0000

Data Index: 506367 (C4 (Web Text))

Max Activating Token Index: 670