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

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

Neuron 821 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0388. Min Act: -0.0005

Data Index: 571100 (C4 (Web Text))

Max Activating Token Index: 1009

Text #1

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0382. Min Act: -0.0005

Data Index: 1200748 (C4 (Web Text))

Max Activating Token Index: 274

Text #2

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0387. Min Act: -0.0005

Data Index: 632633 (C4 (Web Text))

Max Activating Token Index: 759

Text #3

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0385. Min Act: -0.0005

Data Index: 68127 (C4 (Web Text))

Max Activating Token Index: 338

Text #4

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0355. Min Act: -0.0005

Data Index: 288446 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0355. Min Act: -0.0005

Data Index: 838086 (C4 (Web Text))

Max Activating Token Index: 647

Text #6

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0338. Min Act: -0.0005

Data Index: 838001 (C4 (Web Text))

Max Activating Token Index: 351

Text #7

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0328. Min Act: -0.0005

Data Index: 90136 (C4 (Web Text))

Max Activating Token Index: 242

Text #8

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0316. Min Act: -0.0005

Data Index: 326076 (C4 (Web Text))

Max Activating Token Index: 501

Text #9

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0341. Min Act: -0.0005

Data Index: 841877 (C4 (Web Text))

Max Activating Token Index: 497

Text #10

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0340. Min Act: -0.0005

Data Index: 704744 (C4 (Web Text))

Max Activating Token Index: 858

Text #11

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0333. Min Act: -0.0005

Data Index: 102385 (C4 (Web Text))

Max Activating Token Index: 341

Text #12

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0337. Min Act: -0.0005

Data Index: 461852 (C4 (Web Text))

Max Activating Token Index: 702

Text #13

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0326. Min Act: -0.0005

Data Index: 1172061 (C4 (Web Text))

Max Activating Token Index: 705

Text #14

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0303. Min Act: -0.0005

Data Index: 491617 (C4 (Web Text))

Max Activating Token Index: 590

Text #15

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0314. Min Act: -0.0005

Data Index: 822208 (C4 (Web Text))

Max Activating Token Index: 682

Text #16

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0321. Min Act: -0.0005

Data Index: 1140263 (C4 (Web Text))

Max Activating Token Index: 581

Text #17

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0320. Min Act: -0.0005

Data Index: 247168 (C4 (Web Text))

Max Activating Token Index: 311

Text #18

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0307. Min Act: -0.0005

Data Index: 61354 (C4 (Web Text))

Max Activating Token Index: 520

Text #19

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0300. Min Act: -0.0005

Data Index: 605253 (C4 (Web Text))

Max Activating Token Index: 858