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

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

Neuron 5362 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7997. Min Range: -0.7997

Max Act: 0.7942. Min Act: -0.0000

Data Index: 750887 (C4 (Web Text))

Max Activating Token Index: 187

Text #1

Max Range: 0.7997. Min Range: -0.7997

Max Act: 0.7243. Min Act: -0.0000

Data Index: 844495 (C4 (Web Text))

Max Activating Token Index: 680

Text #2

Max Range: 0.7997. Min Range: -0.7997

Max Act: 0.7088. Min Act: -0.0000

Data Index: 617273 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 0.7997. Min Range: -0.7997

Max Act: 0.7997. Min Act: -0.0000

Data Index: 205427 (C4 (Web Text))

Max Activating Token Index: 885

Text #4

Max Range: 0.7997. Min Range: -0.7997

Max Act: 0.6637. Min Act: -0.0000

Data Index: 580397 (C4 (Web Text))

Max Activating Token Index: 715

Text #5

Max Range: 0.7997. Min Range: -0.7997

Max Act: 0.6348. Min Act: -0.0000

Data Index: 1022919 (C4 (Web Text))

Max Activating Token Index: 702

Text #6

Max Range: 0.7997. Min Range: -0.7997

Max Act: 0.6476. Min Act: -0.0000

Data Index: 914360 (C4 (Web Text))

Max Activating Token Index: 489

Text #7

Max Range: 0.7997. Min Range: -0.7997

Max Act: 0.5911. Min Act: -0.0000

Data Index: 1269935 (C4 (Web Text))

Max Activating Token Index: 182

Text #8

Max Range: 0.7997. Min Range: -0.7997

Max Act: 0.5797. Min Act: -0.0000

Data Index: 124120 (C4 (Web Text))

Max Activating Token Index: 1010

Text #9

Max Range: 0.7997. Min Range: -0.7997

Max Act: 0.5074. Min Act: -0.0000

Data Index: 656255 (C4 (Web Text))

Max Activating Token Index: 275

Text #10

Max Range: 0.7997. Min Range: -0.7997

Max Act: 0.5000. Min Act: -0.0000

Data Index: 362539 (C4 (Web Text))

Max Activating Token Index: 1010

Text #11

Max Range: 0.7997. Min Range: -0.7997

Max Act: 0.5396. Min Act: -0.0000

Data Index: 1173138 (C4 (Web Text))

Max Activating Token Index: 573

Text #12

Max Range: 0.7997. Min Range: -0.7997

Max Act: 0.5058. Min Act: -0.0000

Data Index: 1200432 (C4 (Web Text))

Max Activating Token Index: 252

Text #13

Max Range: 0.7997. Min Range: -0.7997

Max Act: 0.5043. Min Act: 0.0000

Data Index: 562263 (C4 (Web Text))

Max Activating Token Index: 572

Text #14

Max Range: 0.7997. Min Range: -0.7997

Max Act: 0.4948. Min Act: -0.0000

Data Index: 162554 (C4 (Web Text))

Max Activating Token Index: 650

Text #15

Max Range: 0.7997. Min Range: -0.7997

Max Act: 0.4885. Min Act: -0.0000

Data Index: 999462 (C4 (Web Text))

Max Activating Token Index: 318

Text #16

Max Range: 0.7997. Min Range: -0.7997

Max Act: 0.4952. Min Act: -0.0000

Data Index: 936842 (C4 (Web Text))

Max Activating Token Index: 251

Text #17

Max Range: 0.7997. Min Range: -0.7997

Max Act: 0.4642. Min Act: -0.0000

Data Index: 589942 (C4 (Web Text))

Max Activating Token Index: 291

Text #18

Max Range: 0.7997. Min Range: -0.7997

Max Act: 0.4444. Min Act: -0.0000

Data Index: 898418 (C4 (Web Text))

Max Activating Token Index: 619

Text #19

Max Range: 0.7997. Min Range: -0.7997

Max Act: 0.4381. Min Act: -0.0000

Data Index: 473585 (C4 (Web Text))

Max Activating Token Index: 949