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

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

Neuron 1202 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: 0.9741. Min Range: -0.9741

Max Act: 0.9741. Min Act: -0.0000

Data Index: 48143 (C4 (Web Text))

Max Activating Token Index: 824

Text #1

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.8540. Min Act: -0.0000

Data Index: 697565 (C4 (Web Text))

Max Activating Token Index: 93

Text #2

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.8231. Min Act: -0.0000

Data Index: 648653 (C4 (Web Text))

Max Activating Token Index: 267

Text #3

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.7943. Min Act: -0.0000

Data Index: 928556 (C4 (Web Text))

Max Activating Token Index: 373

Text #4

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.8212. Min Act: -0.0000

Data Index: 1050467 (C4 (Web Text))

Max Activating Token Index: 268

Text #5

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.7821. Min Act: -0.0000

Data Index: 426232 (C4 (Web Text))

Max Activating Token Index: 540

Text #6

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.7952. Min Act: -0.0000

Data Index: 1045059 (C4 (Web Text))

Max Activating Token Index: 940

Text #7

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.7332. Min Act: -0.0000

Data Index: 1334693 (C4 (Web Text))

Max Activating Token Index: 358

Text #8

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.7975. Min Act: -0.0000

Data Index: 393775 (C4 (Web Text))

Max Activating Token Index: 689

Text #9

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.7647. Min Act: -0.0000

Data Index: 120461 (C4 (Web Text))

Max Activating Token Index: 966

Text #10

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.6956. Min Act: -0.0000

Data Index: 1343357 (C4 (Web Text))

Max Activating Token Index: 1014

Text #11

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.7009. Min Act: -0.0000

Data Index: 772609 (C4 (Web Text))

Max Activating Token Index: 480

Text #12

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.7226. Min Act: -0.0000

Data Index: 540906 (C4 (Web Text))

Max Activating Token Index: 917

Text #13

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.6977. Min Act: -0.0000

Data Index: 151996 (C4 (Web Text))

Max Activating Token Index: 543

Text #14

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.6107. Min Act: -0.0000

Data Index: 428250 (C4 (Web Text))

Max Activating Token Index: 832

Text #15

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.7249. Min Act: -0.0000

Data Index: 848568 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.6537. Min Act: -0.0000

Data Index: 766180 (C4 (Web Text))

Max Activating Token Index: 341

Text #17

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.6623. Min Act: -0.0000

Data Index: 837 (C4 (Web Text))

Max Activating Token Index: 239

Text #18

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.6937. Min Act: -0.0000

Data Index: 426873 (C4 (Web Text))

Max Activating Token Index: 969

Text #19

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.6741. Min Act: -0.0000

Data Index: 952627 (C4 (Web Text))

Max Activating Token Index: 476