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

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

Neuron 2873 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.6443. Min Act: -0.0001

Data Index: 1041337 (C4 (Web Text))

Max Activating Token Index: 489

Text #1

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.6177. Min Act: 0.0000

Data Index: 775983 (C4 (Web Text))

Max Activating Token Index: 52

Text #2

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.6099. Min Act: 0.0000

Data Index: 823181 (C4 (Web Text))

Max Activating Token Index: 211

Text #3

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.5925. Min Act: 0.0000

Data Index: 106860 (C4 (Web Text))

Max Activating Token Index: 395

Text #4

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.6046. Min Act: -0.0000

Data Index: 554289 (C4 (Web Text))

Max Activating Token Index: 504

Text #5

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.5757. Min Act: 0.0000

Data Index: 540437 (C4 (Web Text))

Max Activating Token Index: 963

Text #6

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.5512. Min Act: 0.0000

Data Index: 1272032 (C4 (Web Text))

Max Activating Token Index: 502

Text #7

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.5543. Min Act: -0.0001

Data Index: 1279832 (C4 (Web Text))

Max Activating Token Index: 915

Text #8

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.5227. Min Act: -0.0001

Data Index: 300984 (C4 (Web Text))

Max Activating Token Index: 720

Text #9

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.5189. Min Act: -0.0000

Data Index: 250217 (C4 (Web Text))

Max Activating Token Index: 284

Text #10

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.5020. Min Act: -0.0001

Data Index: 502477 (C4 (Web Text))

Max Activating Token Index: 449

Text #11

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.5158. Min Act: 0.0000

Data Index: 1224100 (C4 (Web Text))

Max Activating Token Index: 248

Text #12

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.4956. Min Act: 0.0000

Data Index: 330038 (C4 (Web Text))

Max Activating Token Index: 293

Text #13

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.4918. Min Act: -0.0001

Data Index: 271808 (C4 (Web Text))

Max Activating Token Index: 850

Text #14

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.4468. Min Act: -0.0001

Data Index: 350324 (C4 (Web Text))

Max Activating Token Index: 665

Text #15

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.4717. Min Act: -0.0001

Data Index: 903252 (C4 (Web Text))

Max Activating Token Index: 753

Text #16

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.4755. Min Act: -0.0000

Data Index: 1149285 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.4714. Min Act: 0.0000

Data Index: 150757 (C4 (Web Text))

Max Activating Token Index: 368

Text #18

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.4678. Min Act: 0.0000

Data Index: 644961 (C4 (Web Text))

Max Activating Token Index: 578

Text #19

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.4591. Min Act: -0.0000

Data Index: 151481 (C4 (Web Text))

Max Activating Token Index: 287