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

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

Neuron 2326 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: 0.5259. Min Range: -0.5259

Max Act: 0.5259. Min Act: -0.0003

Data Index: 1058507 (C4 (Web Text))

Max Activating Token Index: 404

Text #1

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.5007. Min Act: -0.0003

Data Index: 1145039 (C4 (Web Text))

Max Activating Token Index: 663

Text #2

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.5005. Min Act: -0.0002

Data Index: 1278995 (C4 (Web Text))

Max Activating Token Index: 297

Text #3

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.4578. Min Act: -0.0003

Data Index: 439284 (C4 (Web Text))

Max Activating Token Index: 423

Text #4

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.4461. Min Act: -0.0002

Data Index: 496294 (C4 (Web Text))

Max Activating Token Index: 343

Text #5

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.4498. Min Act: -0.0002

Data Index: 805669 (C4 (Web Text))

Max Activating Token Index: 864

Text #6

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.4477. Min Act: -0.0003

Data Index: 451614 (C4 (Web Text))

Max Activating Token Index: 283

Text #7

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.4494. Min Act: -0.0002

Data Index: 814259 (C4 (Web Text))

Max Activating Token Index: 751

Text #8

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.4465. Min Act: -0.0003

Data Index: 1092785 (C4 (Web Text))

Max Activating Token Index: 380

Text #9

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.4336. Min Act: -0.0003

Data Index: 664475 (C4 (Web Text))

Max Activating Token Index: 200

Text #10

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.4362. Min Act: -0.0002

Data Index: 734367 (C4 (Web Text))

Max Activating Token Index: 703

Text #11

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.4240. Min Act: -0.0003

Data Index: 40946 (C4 (Web Text))

Max Activating Token Index: 966

Text #12

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.4275. Min Act: -0.0003

Data Index: 848529 (C4 (Web Text))

Max Activating Token Index: 236

Text #13

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.4315. Min Act: -0.0002

Data Index: 735484 (C4 (Web Text))

Max Activating Token Index: 195

Text #14

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.4244. Min Act: -0.0003

Data Index: 327854 (C4 (Web Text))

Max Activating Token Index: 380

Text #15

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.4255. Min Act: -0.0002

Data Index: 191447 (C4 (Web Text))

Max Activating Token Index: 558

Text #16

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.4135. Min Act: -0.0002

Data Index: 635774 (C4 (Web Text))

Max Activating Token Index: 816

Text #17

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.4163. Min Act: -0.0003

Data Index: 217113 (C4 (Web Text))

Max Activating Token Index: 585

Text #18

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.4140. Min Act: -0.0002

Data Index: 149464 (C4 (Web Text))

Max Activating Token Index: 330

Text #19

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.4047. Min Act: -0.0003

Data Index: 580681 (C4 (Web Text))

Max Activating Token Index: 352