Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1559 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.4647. Min Range: -1.4647

Max Act: 1.4647. Min Act: -0.0003

Data Index: 946011 (C4 (Web Text))

Max Activating Token Index: 359

Text #1

Max Range: 1.4647. Min Range: -1.4647

Max Act: 1.4290. Min Act: -0.0003

Data Index: 608256 (C4 (Web Text))

Max Activating Token Index: 400

Text #2

Max Range: 1.4647. Min Range: -1.4647

Max Act: 1.2067. Min Act: -0.0004

Data Index: 1133122 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 1.4647. Min Range: -1.4647

Max Act: 1.2317. Min Act: -0.0003

Data Index: 1105015 (C4 (Web Text))

Max Activating Token Index: 858

Text #4

Max Range: 1.4647. Min Range: -1.4647

Max Act: 1.4329. Min Act: -0.0003

Data Index: 320085 (C4 (Web Text))

Max Activating Token Index: 643

Text #5

Max Range: 1.4647. Min Range: -1.4647

Max Act: 1.2089. Min Act: -0.0003

Data Index: 942359 (C4 (Web Text))

Max Activating Token Index: 421

Text #6

Max Range: 1.4647. Min Range: -1.4647

Max Act: 1.2120. Min Act: -0.0003

Data Index: 498862 (C4 (Web Text))

Max Activating Token Index: 894

Text #7

Max Range: 1.4647. Min Range: -1.4647

Max Act: 0.9556. Min Act: -0.0003

Data Index: 268148 (C4 (Web Text))

Max Activating Token Index: 838

Text #8

Max Range: 1.4647. Min Range: -1.4647

Max Act: 0.9841. Min Act: -0.0003

Data Index: 1022452 (C4 (Web Text))

Max Activating Token Index: 659

Text #9

Max Range: 1.4647. Min Range: -1.4647

Max Act: 1.1074. Min Act: -0.0004

Data Index: 971794 (C4 (Web Text))

Max Activating Token Index: 73

Text #10

Max Range: 1.4647. Min Range: -1.4647

Max Act: 0.7797. Min Act: -0.0003

Data Index: 530949 (C4 (Web Text))

Max Activating Token Index: 611

Text #11

Max Range: 1.4647. Min Range: -1.4647

Max Act: 1.1659. Min Act: -0.0003

Data Index: 833528 (C4 (Web Text))

Max Activating Token Index: 939

Text #12

Max Range: 1.4647. Min Range: -1.4647

Max Act: 1.0947. Min Act: -0.0004

Data Index: 429327 (C4 (Web Text))

Max Activating Token Index: 79

Text #13

Max Range: 1.4647. Min Range: -1.4647

Max Act: 1.2577. Min Act: -0.0003

Data Index: 579838 (C4 (Web Text))

Max Activating Token Index: 169

Text #14

Max Range: 1.4647. Min Range: -1.4647

Max Act: 1.1994. Min Act: -0.0003

Data Index: 1245229 (C4 (Web Text))

Max Activating Token Index: 338

Text #15

Max Range: 1.4647. Min Range: -1.4647

Max Act: 1.1973. Min Act: -0.0003

Data Index: 357513 (C4 (Web Text))

Max Activating Token Index: 954

Text #16

Max Range: 1.4647. Min Range: -1.4647

Max Act: 1.1173. Min Act: -0.0003

Data Index: 1006796 (C4 (Web Text))

Max Activating Token Index: 216

Text #17

Max Range: 1.4647. Min Range: -1.4647

Max Act: 1.1136. Min Act: -0.0003

Data Index: 99388 (C4 (Web Text))

Max Activating Token Index: 163

Text #18

Max Range: 1.4647. Min Range: -1.4647

Max Act: 1.0666. Min Act: -0.0003

Data Index: 303429 (C4 (Web Text))

Max Activating Token Index: 800

Text #19

Max Range: 1.4647. Min Range: -1.4647

Max Act: 1.1599. Min Act: -0.0003

Data Index: 675021 (C4 (Web Text))

Max Activating Token Index: 351