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

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

Neuron 2330 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.6208. Min Range: -1.6208

Max Act: 1.6208. Min Act: -0.0002

Data Index: 625506 (C4 (Web Text))

Max Activating Token Index: 583

Text #1

Max Range: 1.6208. Min Range: -1.6208

Max Act: 1.5611. Min Act: -0.0002

Data Index: 475813 (C4 (Web Text))

Max Activating Token Index: 360

Text #2

Max Range: 1.6208. Min Range: -1.6208

Max Act: 1.4411. Min Act: -0.0002

Data Index: 208705 (C4 (Web Text))

Max Activating Token Index: 924

Text #3

Max Range: 1.6208. Min Range: -1.6208

Max Act: 1.4502. Min Act: -0.0002

Data Index: 153609 (C4 (Web Text))

Max Activating Token Index: 429

Text #4

Max Range: 1.6208. Min Range: -1.6208

Max Act: 1.3942. Min Act: -0.0002

Data Index: 473899 (C4 (Web Text))

Max Activating Token Index: 4

Text #5

Max Range: 1.6208. Min Range: -1.6208

Max Act: 1.3812. Min Act: -0.0002

Data Index: 229178 (C4 (Web Text))

Max Activating Token Index: 339

Text #6

Max Range: 1.6208. Min Range: -1.6208

Max Act: 1.3628. Min Act: -0.0002

Data Index: 1058268 (C4 (Web Text))

Max Activating Token Index: 490

Text #7

Max Range: 1.6208. Min Range: -1.6208

Max Act: 1.3612. Min Act: -0.0002

Data Index: 123023 (C4 (Web Text))

Max Activating Token Index: 280

Text #8

Max Range: 1.6208. Min Range: -1.6208

Max Act: 1.3805. Min Act: -0.0002

Data Index: 38001 (C4 (Web Text))

Max Activating Token Index: 457

Text #9

Max Range: 1.6208. Min Range: -1.6208

Max Act: 1.3535. Min Act: -0.0002

Data Index: 245210 (C4 (Web Text))

Max Activating Token Index: 383

Text #10

Max Range: 1.6208. Min Range: -1.6208

Max Act: 1.3446. Min Act: -0.0002

Data Index: 1226301 (C4 (Web Text))

Max Activating Token Index: 566

Text #11

Max Range: 1.6208. Min Range: -1.6208

Max Act: 1.3148. Min Act: -0.0002

Data Index: 633033 (C4 (Web Text))

Max Activating Token Index: 965

Text #12

Max Range: 1.6208. Min Range: -1.6208

Max Act: 1.3298. Min Act: -0.0002

Data Index: 8527 (C4 (Web Text))

Max Activating Token Index: 873

Text #13

Max Range: 1.6208. Min Range: -1.6208

Max Act: 1.3001. Min Act: -0.0002

Data Index: 772614 (C4 (Web Text))

Max Activating Token Index: 465

Text #14

Max Range: 1.6208. Min Range: -1.6208

Max Act: 1.3365. Min Act: -0.0002

Data Index: 368569 (C4 (Web Text))

Max Activating Token Index: 199

Text #15

Max Range: 1.6208. Min Range: -1.6208

Max Act: 1.3108. Min Act: -0.0002

Data Index: 452697 (C4 (Web Text))

Max Activating Token Index: 38

Text #16

Max Range: 1.6208. Min Range: -1.6208

Max Act: 1.3237. Min Act: -0.0002

Data Index: 379926 (C4 (Web Text))

Max Activating Token Index: 222

Text #17

Max Range: 1.6208. Min Range: -1.6208

Max Act: 1.3071. Min Act: -0.0002

Data Index: 1008523 (C4 (Web Text))

Max Activating Token Index: 428

Text #18

Max Range: 1.6208. Min Range: -1.6208

Max Act: 1.3323. Min Act: -0.0002

Data Index: 1155222 (C4 (Web Text))

Max Activating Token Index: 792

Text #19

Max Range: 1.6208. Min Range: -1.6208

Max Act: 1.2954. Min Act: -0.0002

Data Index: 517460 (C4 (Web Text))

Max Activating Token Index: 73