Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2786 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.7922. Min Range: -1.7922

Max Act: 1.7922. Min Act: -0.0001

Data Index: 358857 (C4 (Web Text))

Max Activating Token Index: 519

Text #1

Max Range: 1.7922. Min Range: -1.7922

Max Act: 1.6881. Min Act: -0.0001

Data Index: 833553 (C4 (Web Text))

Max Activating Token Index: 595

Text #2

Max Range: 1.7922. Min Range: -1.7922

Max Act: 1.6205. Min Act: -0.0001

Data Index: 4514 (C4 (Web Text))

Max Activating Token Index: 349

Text #3

Max Range: 1.7922. Min Range: -1.7922

Max Act: 1.6594. Min Act: -0.0001

Data Index: 954785 (C4 (Web Text))

Max Activating Token Index: 225

Text #4

Max Range: 1.7922. Min Range: -1.7922

Max Act: 1.5234. Min Act: -0.0001

Data Index: 430885 (C4 (Web Text))

Max Activating Token Index: 685

Text #5

Max Range: 1.7922. Min Range: -1.7922

Max Act: 1.4138. Min Act: -0.0001

Data Index: 585363 (C4 (Web Text))

Max Activating Token Index: 787

Text #6

Max Range: 1.7922. Min Range: -1.7922

Max Act: 1.4493. Min Act: -0.0001

Data Index: 852247 (C4 (Web Text))

Max Activating Token Index: 876

Text #7

Max Range: 1.7922. Min Range: -1.7922

Max Act: 1.3889. Min Act: -0.0001

Data Index: 59683 (C4 (Web Text))

Max Activating Token Index: 640

Text #8

Max Range: 1.7922. Min Range: -1.7922

Max Act: 1.4444. Min Act: -0.0001

Data Index: 310686 (C4 (Web Text))

Max Activating Token Index: 389

Text #9

Max Range: 1.7922. Min Range: -1.7922

Max Act: 1.4981. Min Act: -0.0001

Data Index: 901054 (C4 (Web Text))

Max Activating Token Index: 935

Text #10

Max Range: 1.7922. Min Range: -1.7922

Max Act: 1.4012. Min Act: -0.0001

Data Index: 40521 (C4 (Web Text))

Max Activating Token Index: 316

Text #11

Max Range: 1.7922. Min Range: -1.7922

Max Act: 1.3771. Min Act: -0.0001

Data Index: 1357558 (C4 (Web Text))

Max Activating Token Index: 255

Text #12

Max Range: 1.7922. Min Range: -1.7922

Max Act: 1.3705. Min Act: -0.0000

Data Index: 546594 (C4 (Web Text))

Max Activating Token Index: 20

Text #13

Max Range: 1.7922. Min Range: -1.7922

Max Act: 1.3191. Min Act: -0.0001

Data Index: 637063 (C4 (Web Text))

Max Activating Token Index: 708

Text #14

Max Range: 1.7922. Min Range: -1.7922

Max Act: 1.3442. Min Act: -0.0001

Data Index: 142516 (C4 (Web Text))

Max Activating Token Index: 767

Text #15

Max Range: 1.7922. Min Range: -1.7922

Max Act: 1.4270. Min Act: -0.0000

Data Index: 896425 (C4 (Web Text))

Max Activating Token Index: 136

Text #16

Max Range: 1.7922. Min Range: -1.7922

Max Act: 1.2694. Min Act: -0.0001

Data Index: 237752 (C4 (Web Text))

Max Activating Token Index: 862

Text #17

Max Range: 1.7922. Min Range: -1.7922

Max Act: 1.3032. Min Act: -0.0001

Data Index: 482400 (C4 (Web Text))

Max Activating Token Index: 248

Text #18

Max Range: 1.7922. Min Range: -1.7922

Max Act: 1.2916. Min Act: -0.0001

Data Index: 378236 (C4 (Web Text))

Max Activating Token Index: 28

Text #19

Max Range: 1.7922. Min Range: -1.7922

Max Act: 1.2843. Min Act: -0.0001

Data Index: 361673 (C4 (Web Text))

Max Activating Token Index: 408