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

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

Neuron 2412 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: 0.5007. Min Range: -0.5007

Max Act: 0.5007. Min Act: -0.0000

Data Index: 425743 (C4 (Web Text))

Max Activating Token Index: 492

Text #1

Max Range: 0.5007. Min Range: -0.5007

Max Act: 0.4138. Min Act: -0.0000

Data Index: 866853 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 0.5007. Min Range: -0.5007

Max Act: 0.4054. Min Act: -0.0001

Data Index: 586427 (C4 (Web Text))

Max Activating Token Index: 764

Text #3

Max Range: 0.5007. Min Range: -0.5007

Max Act: 0.3184. Min Act: -0.0001

Data Index: 748838 (C4 (Web Text))

Max Activating Token Index: 504

Text #4

Max Range: 0.5007. Min Range: -0.5007

Max Act: 0.2890. Min Act: -0.0001

Data Index: 941436 (C4 (Web Text))

Max Activating Token Index: 810

Text #5

Max Range: 0.5007. Min Range: -0.5007

Max Act: 0.2912. Min Act: -0.0001

Data Index: 160702 (C4 (Web Text))

Max Activating Token Index: 658

Text #6

Max Range: 0.5007. Min Range: -0.5007

Max Act: 0.3032. Min Act: -0.0001

Data Index: 996253 (C4 (Web Text))

Max Activating Token Index: 652

Text #7

Max Range: 0.5007. Min Range: -0.5007

Max Act: 0.3033. Min Act: -0.0001

Data Index: 286273 (C4 (Web Text))

Max Activating Token Index: 631

Text #8

Max Range: 0.5007. Min Range: -0.5007

Max Act: 0.3029. Min Act: -0.0001

Data Index: 1327093 (C4 (Web Text))

Max Activating Token Index: 616

Text #9

Max Range: 0.5007. Min Range: -0.5007

Max Act: 0.3301. Min Act: -0.0001

Data Index: 774154 (C4 (Web Text))

Max Activating Token Index: 36

Text #10

Max Range: 0.5007. Min Range: -0.5007

Max Act: 0.3002. Min Act: -0.0001

Data Index: 1044857 (C4 (Web Text))

Max Activating Token Index: 574

Text #11

Max Range: 0.5007. Min Range: -0.5007

Max Act: 0.2892. Min Act: -0.0001

Data Index: 501073 (C4 (Web Text))

Max Activating Token Index: 930

Text #12

Max Range: 0.5007. Min Range: -0.5007

Max Act: 0.2964. Min Act: -0.0001

Data Index: 334983 (C4 (Web Text))

Max Activating Token Index: 3

Text #13

Max Range: 0.5007. Min Range: -0.5007

Max Act: 0.2893. Min Act: -0.0001

Data Index: 958553 (C4 (Web Text))

Max Activating Token Index: 337

Text #14

Max Range: 0.5007. Min Range: -0.5007

Max Act: 0.2770. Min Act: -0.0001

Data Index: 683319 (C4 (Web Text))

Max Activating Token Index: 561

Text #15

Max Range: 0.5007. Min Range: -0.5007

Max Act: 0.2566. Min Act: -0.0001

Data Index: 619202 (C4 (Web Text))

Max Activating Token Index: 416

Text #16

Max Range: 0.5007. Min Range: -0.5007

Max Act: 0.2717. Min Act: -0.0001

Data Index: 25199 (C4 (Web Text))

Max Activating Token Index: 480

Text #17

Max Range: 0.5007. Min Range: -0.5007

Max Act: 0.2970. Min Act: -0.0001

Data Index: 1154078 (C4 (Web Text))

Max Activating Token Index: 693

Text #18

Max Range: 0.5007. Min Range: -0.5007

Max Act: 0.2589. Min Act: -0.0001

Data Index: 112177 (C4 (Web Text))

Max Activating Token Index: 306

Text #19

Max Range: 0.5007. Min Range: -0.5007

Max Act: 0.2748. Min Act: -0.0001

Data Index: 808361 (C4 (Web Text))

Max Activating Token Index: 744