Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3451 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0400. Min Act: -0.0001

Data Index: 65170 (C4 (Web Text))

Max Activating Token Index: 614

Text #1

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0360. Min Act: -0.0001

Data Index: 1216404 (C4 (Web Text))

Max Activating Token Index: 830

Text #2

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0368. Min Act: -0.0001

Data Index: 964948 (C4 (Web Text))

Max Activating Token Index: 613

Text #3

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0362. Min Act: -0.0001

Data Index: 1058938 (C4 (Web Text))

Max Activating Token Index: 686

Text #4

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0373. Min Act: -0.0001

Data Index: 1281173 (C4 (Web Text))

Max Activating Token Index: 355

Text #5

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0327. Min Act: -0.0001

Data Index: 425928 (C4 (Web Text))

Max Activating Token Index: 376

Text #6

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0336. Min Act: -0.0001

Data Index: 561784 (C4 (Web Text))

Max Activating Token Index: 791

Text #7

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0290. Min Act: -0.0001

Data Index: 373179 (C4 (Web Text))

Max Activating Token Index: 792

Text #8

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0326. Min Act: -0.0001

Data Index: 617920 (C4 (Web Text))

Max Activating Token Index: 896

Text #9

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0344. Min Act: -0.0001

Data Index: 338651 (C4 (Web Text))

Max Activating Token Index: 420

Text #10

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0339. Min Act: -0.0001

Data Index: 323991 (C4 (Web Text))

Max Activating Token Index: 861

Text #11

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0331. Min Act: -0.0001

Data Index: 1396450 (Python Code)

Max Activating Token Index: 755

Text #12

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0313. Min Act: -0.0001

Data Index: 1280551 (C4 (Web Text))

Max Activating Token Index: 630

Text #13

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0303. Min Act: -0.0001

Data Index: 289470 (C4 (Web Text))

Max Activating Token Index: 116

Text #14

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0282. Min Act: -0.0001

Data Index: 995625 (C4 (Web Text))

Max Activating Token Index: 489

Text #15

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0279. Min Act: -0.0001

Data Index: 785907 (C4 (Web Text))

Max Activating Token Index: 141

Text #16

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0303. Min Act: -0.0001

Data Index: 506161 (C4 (Web Text))

Max Activating Token Index: 399

Text #17

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0311. Min Act: -0.0001

Data Index: 121107 (C4 (Web Text))

Max Activating Token Index: 807

Text #18

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0268. Min Act: -0.0001

Data Index: 79528 (C4 (Web Text))

Max Activating Token Index: 187

Text #19

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0325. Min Act: -0.0001

Data Index: 648532 (C4 (Web Text))

Max Activating Token Index: 877