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

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

Neuron 533 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0464. Min Act: -0.0001

Data Index: 990447 (C4 (Web Text))

Max Activating Token Index: 523

Text #1

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0405. Min Act: -0.0001

Data Index: 917563 (C4 (Web Text))

Max Activating Token Index: 6

Text #2

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0386. Min Act: -0.0001

Data Index: 266552 (C4 (Web Text))

Max Activating Token Index: 227

Text #3

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0397. Min Act: -0.0001

Data Index: 290255 (C4 (Web Text))

Max Activating Token Index: 4

Text #4

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0400. Min Act: -0.0001

Data Index: 205777 (C4 (Web Text))

Max Activating Token Index: 328

Text #5

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0345. Min Act: -0.0001

Data Index: 1032876 (C4 (Web Text))

Max Activating Token Index: 857

Text #6

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0398. Min Act: -0.0001

Data Index: 336300 (C4 (Web Text))

Max Activating Token Index: 803

Text #7

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0369. Min Act: -0.0001

Data Index: 359223 (C4 (Web Text))

Max Activating Token Index: 162

Text #8

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0377. Min Act: -0.0001

Data Index: 272489 (C4 (Web Text))

Max Activating Token Index: 463

Text #9

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0350. Min Act: -0.0001

Data Index: 1061774 (C4 (Web Text))

Max Activating Token Index: 13

Text #10

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0367. Min Act: -0.0001

Data Index: 368797 (C4 (Web Text))

Max Activating Token Index: 821

Text #11

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0360. Min Act: -0.0001

Data Index: 1050289 (C4 (Web Text))

Max Activating Token Index: 165

Text #12

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0349. Min Act: -0.0001

Data Index: 988059 (C4 (Web Text))

Max Activating Token Index: 429

Text #13

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0316. Min Act: -0.0001

Data Index: 50238 (C4 (Web Text))

Max Activating Token Index: 268

Text #14

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0339. Min Act: -0.0001

Data Index: 467323 (C4 (Web Text))

Max Activating Token Index: 6

Text #15

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0346. Min Act: -0.0001

Data Index: 257018 (C4 (Web Text))

Max Activating Token Index: 308

Text #16

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0361. Min Act: -0.0001

Data Index: 1111839 (C4 (Web Text))

Max Activating Token Index: 640

Text #17

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0293. Min Act: -0.0001

Data Index: 564394 (C4 (Web Text))

Max Activating Token Index: 204

Text #18

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0319. Min Act: -0.0001

Data Index: 532235 (C4 (Web Text))

Max Activating Token Index: 202

Text #19

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0310. Min Act: -0.0001

Data Index: 901124 (C4 (Web Text))

Max Activating Token Index: 776