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

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

Neuron 765 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3661. Min Range: -2.3661

Max Act: 2.2693. Min Act: -0.0000

Data Index: 75089 (C4 (Web Text))

Max Activating Token Index: 320

Text #1

Max Range: 2.3661. Min Range: -2.3661

Max Act: 2.2723. Min Act: -0.0000

Data Index: 393405 (C4 (Web Text))

Max Activating Token Index: 536

Text #2

Max Range: 2.3661. Min Range: -2.3661

Max Act: 2.3661. Min Act: -0.0000

Data Index: 864461 (C4 (Web Text))

Max Activating Token Index: 676

Text #3

Max Range: 2.3661. Min Range: -2.3661

Max Act: 2.1261. Min Act: -0.0000

Data Index: 716085 (C4 (Web Text))

Max Activating Token Index: 854

Text #4

Max Range: 2.3661. Min Range: -2.3661

Max Act: 2.3427. Min Act: -0.0000

Data Index: 55669 (C4 (Web Text))

Max Activating Token Index: 525

Text #5

Max Range: 2.3661. Min Range: -2.3661

Max Act: 2.2104. Min Act: -0.0000

Data Index: 240781 (C4 (Web Text))

Max Activating Token Index: 545

Text #6

Max Range: 2.3661. Min Range: -2.3661

Max Act: 2.1546. Min Act: -0.0000

Data Index: 995832 (C4 (Web Text))

Max Activating Token Index: 431

Text #7

Max Range: 2.3661. Min Range: -2.3661

Max Act: 2.0395. Min Act: -0.0000

Data Index: 735882 (C4 (Web Text))

Max Activating Token Index: 141

Text #8

Max Range: 2.3661. Min Range: -2.3661

Max Act: 2.1131. Min Act: -0.0000

Data Index: 559858 (C4 (Web Text))

Max Activating Token Index: 184

Text #9

Max Range: 2.3661. Min Range: -2.3661

Max Act: 2.0274. Min Act: -0.0000

Data Index: 703947 (C4 (Web Text))

Max Activating Token Index: 329

Text #10

Max Range: 2.3661. Min Range: -2.3661

Max Act: 2.0284. Min Act: -0.0000

Data Index: 1015904 (C4 (Web Text))

Max Activating Token Index: 938

Text #11

Max Range: 2.3661. Min Range: -2.3661

Max Act: 1.9119. Min Act: -0.0000

Data Index: 260949 (C4 (Web Text))

Max Activating Token Index: 166

Text #12

Max Range: 2.3661. Min Range: -2.3661

Max Act: 2.0054. Min Act: -0.0000

Data Index: 298647 (C4 (Web Text))

Max Activating Token Index: 240

Text #13

Max Range: 2.3661. Min Range: -2.3661

Max Act: 1.8881. Min Act: -0.0000

Data Index: 936928 (C4 (Web Text))

Max Activating Token Index: 348

Text #14

Max Range: 2.3661. Min Range: -2.3661

Max Act: 1.9685. Min Act: -0.0000

Data Index: 57288 (C4 (Web Text))

Max Activating Token Index: 526

Text #15

Max Range: 2.3661. Min Range: -2.3661

Max Act: 1.9612. Min Act: -0.0000

Data Index: 214175 (C4 (Web Text))

Max Activating Token Index: 829

Text #16

Max Range: 2.3661. Min Range: -2.3661

Max Act: 1.9512. Min Act: -0.0000

Data Index: 1489406 (Python Code)

Max Activating Token Index: 98

Text #17

Max Range: 2.3661. Min Range: -2.3661

Max Act: 1.9328. Min Act: -0.0000

Data Index: 371523 (C4 (Web Text))

Max Activating Token Index: 716

Text #18

Max Range: 2.3661. Min Range: -2.3661

Max Act: 1.9041. Min Act: -0.0000

Data Index: 390268 (C4 (Web Text))

Max Activating Token Index: 455

Text #19

Max Range: 2.3661. Min Range: -2.3661

Max Act: 1.8988. Min Act: -0.0000

Data Index: 1356928 (C4 (Web Text))

Max Activating Token Index: 435