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

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

Neuron 2709 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0810. Min Range: -3.0810

Max Act: 3.0430. Min Act: -0.0001

Data Index: 774465 (C4 (Web Text))

Max Activating Token Index: 6

Text #1

Max Range: 3.0810. Min Range: -3.0810

Max Act: 3.0810. Min Act: -0.0000

Data Index: 403540 (C4 (Web Text))

Max Activating Token Index: 613

Text #2

Max Range: 3.0810. Min Range: -3.0810

Max Act: 2.5654. Min Act: -0.0000

Data Index: 1349290 (C4 (Web Text))

Max Activating Token Index: 894

Text #3

Max Range: 3.0810. Min Range: -3.0810

Max Act: 2.6701. Min Act: -0.0001

Data Index: 892571 (C4 (Web Text))

Max Activating Token Index: 551

Text #4

Max Range: 3.0810. Min Range: -3.0810

Max Act: 2.7684. Min Act: -0.0001

Data Index: 314541 (C4 (Web Text))

Max Activating Token Index: 202

Text #5

Max Range: 3.0810. Min Range: -3.0810

Max Act: 2.7665. Min Act: -0.0001

Data Index: 766496 (C4 (Web Text))

Max Activating Token Index: 550

Text #6

Max Range: 3.0810. Min Range: -3.0810

Max Act: 2.4012. Min Act: -0.0001

Data Index: 485298 (C4 (Web Text))

Max Activating Token Index: 742

Text #7

Max Range: 3.0810. Min Range: -3.0810

Max Act: 2.6664. Min Act: -0.0000

Data Index: 1151496 (C4 (Web Text))

Max Activating Token Index: 763

Text #8

Max Range: 3.0810. Min Range: -3.0810

Max Act: 2.5745. Min Act: -0.0001

Data Index: 134782 (C4 (Web Text))

Max Activating Token Index: 746

Text #9

Max Range: 3.0810. Min Range: -3.0810

Max Act: 2.2110. Min Act: -0.0001

Data Index: 55904 (C4 (Web Text))

Max Activating Token Index: 522

Text #10

Max Range: 3.0810. Min Range: -3.0810

Max Act: 2.3372. Min Act: -0.0000

Data Index: 906932 (C4 (Web Text))

Max Activating Token Index: 295

Text #11

Max Range: 3.0810. Min Range: -3.0810

Max Act: 2.1697. Min Act: -0.0001

Data Index: 641577 (C4 (Web Text))

Max Activating Token Index: 931

Text #12

Max Range: 3.0810. Min Range: -3.0810

Max Act: 2.3435. Min Act: -0.0000

Data Index: 56072 (C4 (Web Text))

Max Activating Token Index: 672

Text #13

Max Range: 3.0810. Min Range: -3.0810

Max Act: 2.3742. Min Act: -0.0001

Data Index: 204281 (C4 (Web Text))

Max Activating Token Index: 175

Text #14

Max Range: 3.0810. Min Range: -3.0810

Max Act: 2.2998. Min Act: -0.0001

Data Index: 1000758 (C4 (Web Text))

Max Activating Token Index: 370

Text #15

Max Range: 3.0810. Min Range: -3.0810

Max Act: 2.0426. Min Act: -0.0000

Data Index: 306162 (C4 (Web Text))

Max Activating Token Index: 384

Text #16

Max Range: 3.0810. Min Range: -3.0810

Max Act: 2.2555. Min Act: -0.0000

Data Index: 364713 (C4 (Web Text))

Max Activating Token Index: 669

Text #17

Max Range: 3.0810. Min Range: -3.0810

Max Act: 2.3879. Min Act: -0.0001

Data Index: 567238 (C4 (Web Text))

Max Activating Token Index: 200

Text #18

Max Range: 3.0810. Min Range: -3.0810

Max Act: 2.2349. Min Act: -0.0001

Data Index: 1288967 (C4 (Web Text))

Max Activating Token Index: 481

Text #19

Max Range: 3.0810. Min Range: -3.0810

Max Act: 2.0226. Min Act: -0.0001

Data Index: 691450 (C4 (Web Text))

Max Activating Token Index: 410