Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 58 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0278. Min Act: -0.0005

Data Index: 235087 (C4 (Web Text))

Max Activating Token Index: 192

Text #1

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0262. Min Act: -0.0006

Data Index: 222046 (C4 (Web Text))

Max Activating Token Index: 627

Text #2

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0267. Min Act: -0.0006

Data Index: 1267965 (C4 (Web Text))

Max Activating Token Index: 236

Text #3

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0259. Min Act: -0.0005

Data Index: 987618 (C4 (Web Text))

Max Activating Token Index: 263

Text #4

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0270. Min Act: -0.0005

Data Index: 138440 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0263. Min Act: -0.0005

Data Index: 427521 (C4 (Web Text))

Max Activating Token Index: 408

Text #6

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0252. Min Act: -0.0005

Data Index: 1348326 (C4 (Web Text))

Max Activating Token Index: 487

Text #7

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0250. Min Act: -0.0005

Data Index: 1220015 (C4 (Web Text))

Max Activating Token Index: 382

Text #8

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0248. Min Act: -0.0005

Data Index: 400224 (C4 (Web Text))

Max Activating Token Index: 433

Text #9

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0248. Min Act: -0.0005

Data Index: 1044009 (C4 (Web Text))

Max Activating Token Index: 478

Text #10

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0252. Min Act: -0.0005

Data Index: 319443 (C4 (Web Text))

Max Activating Token Index: 187

Text #11

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0257. Min Act: -0.0005

Data Index: 1023225 (C4 (Web Text))

Max Activating Token Index: 386

Text #12

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0250. Min Act: -0.0005

Data Index: 979311 (C4 (Web Text))

Max Activating Token Index: 135

Text #13

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0250. Min Act: -0.0005

Data Index: 284076 (C4 (Web Text))

Max Activating Token Index: 345

Text #14

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0255. Min Act: -0.0005

Data Index: 875919 (C4 (Web Text))

Max Activating Token Index: 267

Text #15

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0249. Min Act: -0.0006

Data Index: 1340638 (C4 (Web Text))

Max Activating Token Index: 692

Text #16

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0247. Min Act: -0.0005

Data Index: 876953 (C4 (Web Text))

Max Activating Token Index: 500

Text #17

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0246. Min Act: -0.0005

Data Index: 438421 (C4 (Web Text))

Max Activating Token Index: 309

Text #18

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0247. Min Act: -0.0006

Data Index: 784303 (C4 (Web Text))

Max Activating Token Index: 293

Text #19

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0246. Min Act: -0.0005

Data Index: 267397 (C4 (Web Text))

Max Activating Token Index: 232