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

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

Neuron 1783 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0388. Min Act: -0.0001

Data Index: 162337 (C4 (Web Text))

Max Activating Token Index: 947

Text #1

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0390. Min Act: -0.0001

Data Index: 909065 (C4 (Web Text))

Max Activating Token Index: 480

Text #2

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0398. Min Act: -0.0001

Data Index: 546508 (C4 (Web Text))

Max Activating Token Index: 174

Text #3

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0392. Min Act: -0.0001

Data Index: 861832 (C4 (Web Text))

Max Activating Token Index: 317

Text #4

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0362. Min Act: -0.0001

Data Index: 1141203 (C4 (Web Text))

Max Activating Token Index: 5

Text #5

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0354. Min Act: -0.0001

Data Index: 489924 (C4 (Web Text))

Max Activating Token Index: 398

Text #6

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0345. Min Act: -0.0001

Data Index: 634030 (C4 (Web Text))

Max Activating Token Index: 120

Text #7

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0358. Min Act: -0.0001

Data Index: 1224342 (C4 (Web Text))

Max Activating Token Index: 635

Text #8

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0346. Min Act: -0.0001

Data Index: 57615 (C4 (Web Text))

Max Activating Token Index: 670

Text #9

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0357. Min Act: -0.0001

Data Index: 851738 (C4 (Web Text))

Max Activating Token Index: 204

Text #10

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0341. Min Act: -0.0001

Data Index: 1331204 (C4 (Web Text))

Max Activating Token Index: 353

Text #11

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0326. Min Act: -0.0001

Data Index: 997662 (C4 (Web Text))

Max Activating Token Index: 48

Text #12

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0340. Min Act: -0.0001

Data Index: 1069188 (C4 (Web Text))

Max Activating Token Index: 478

Text #13

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0346. Min Act: -0.0001

Data Index: 1478341 (Python Code)

Max Activating Token Index: 270

Text #14

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0336. Min Act: -0.0001

Data Index: 507591 (C4 (Web Text))

Max Activating Token Index: 537

Text #15

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0346. Min Act: -0.0001

Data Index: 1146559 (C4 (Web Text))

Max Activating Token Index: 868

Text #16

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0337. Min Act: -0.0001

Data Index: 242675 (C4 (Web Text))

Max Activating Token Index: 107

Text #17

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0342. Min Act: -0.0001

Data Index: 898375 (C4 (Web Text))

Max Activating Token Index: 972

Text #18

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0340. Min Act: -0.0001

Data Index: 946122 (C4 (Web Text))

Max Activating Token Index: 327

Text #19

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0318. Min Act: -0.0001

Data Index: 211216 (C4 (Web Text))

Max Activating Token Index: 560