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

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

Neuron 321 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0511. Min Act: -0.0006

Data Index: 93244 (C4 (Web Text))

Max Activating Token Index: 459

Text #1

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0432. Min Act: -0.0006

Data Index: 149199 (C4 (Web Text))

Max Activating Token Index: 552

Text #2

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0441. Min Act: -0.0006

Data Index: 1259947 (C4 (Web Text))

Max Activating Token Index: 861

Text #3

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0405. Min Act: -0.0006

Data Index: 727239 (C4 (Web Text))

Max Activating Token Index: 217

Text #4

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0397. Min Act: -0.0006

Data Index: 44074 (C4 (Web Text))

Max Activating Token Index: 619

Text #5

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0414. Min Act: -0.0006

Data Index: 1339388 (C4 (Web Text))

Max Activating Token Index: 318

Text #6

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0371. Min Act: -0.0006

Data Index: 1081268 (C4 (Web Text))

Max Activating Token Index: 54

Text #7

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0368. Min Act: -0.0006

Data Index: 1975 (C4 (Web Text))

Max Activating Token Index: 803

Text #8

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0383. Min Act: -0.0006

Data Index: 566740 (C4 (Web Text))

Max Activating Token Index: 370

Text #9

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0371. Min Act: -0.0006

Data Index: 1271008 (C4 (Web Text))

Max Activating Token Index: 536

Text #10

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0368. Min Act: -0.0006

Data Index: 746142 (C4 (Web Text))

Max Activating Token Index: 437

Text #11

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0357. Min Act: -0.0006

Data Index: 203459 (C4 (Web Text))

Max Activating Token Index: 297

Text #12

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0363. Min Act: -0.0006

Data Index: 1067184 (C4 (Web Text))

Max Activating Token Index: 51

Text #13

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0356. Min Act: -0.0006

Data Index: 524197 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0338. Min Act: -0.0006

Data Index: 820492 (C4 (Web Text))

Max Activating Token Index: 249

Text #15

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0359. Min Act: -0.0006

Data Index: 1280811 (C4 (Web Text))

Max Activating Token Index: 944

Text #16

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0342. Min Act: -0.0006

Data Index: 127046 (C4 (Web Text))

Max Activating Token Index: 601

Text #17

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0342. Min Act: -0.0006

Data Index: 502176 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0351. Min Act: -0.0006

Data Index: 1219956 (C4 (Web Text))

Max Activating Token Index: 864

Text #19

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0344. Min Act: -0.0006

Data Index: 1003317 (C4 (Web Text))

Max Activating Token Index: 459