Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 470 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0297. Min Act: -0.0005

Data Index: 168930 (C4 (Web Text))

Max Activating Token Index: 738

Text #1

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0298. Min Act: -0.0005

Data Index: 1291881 (C4 (Web Text))

Max Activating Token Index: 596

Text #2

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0290. Min Act: -0.0006

Data Index: 226475 (C4 (Web Text))

Max Activating Token Index: 466

Text #3

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0295. Min Act: -0.0006

Data Index: 713760 (C4 (Web Text))

Max Activating Token Index: 600

Text #4

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0283. Min Act: -0.0006

Data Index: 703896 (C4 (Web Text))

Max Activating Token Index: 355

Text #5

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0284. Min Act: -0.0006

Data Index: 312687 (C4 (Web Text))

Max Activating Token Index: 435

Text #6

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0292. Min Act: -0.0006

Data Index: 989372 (C4 (Web Text))

Max Activating Token Index: 965

Text #7

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0271. Min Act: -0.0006

Data Index: 142733 (C4 (Web Text))

Max Activating Token Index: 336

Text #8

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0275. Min Act: -0.0006

Data Index: 1109189 (C4 (Web Text))

Max Activating Token Index: 987

Text #9

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0280. Min Act: -0.0006

Data Index: 141230 (C4 (Web Text))

Max Activating Token Index: 703

Text #10

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0273. Min Act: -0.0006

Data Index: 459615 (C4 (Web Text))

Max Activating Token Index: 951

Text #11

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0272. Min Act: -0.0006

Data Index: 393140 (C4 (Web Text))

Max Activating Token Index: 340

Text #12

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0278. Min Act: -0.0006

Data Index: 369905 (C4 (Web Text))

Max Activating Token Index: 680

Text #13

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0278. Min Act: -0.0006

Data Index: 593923 (C4 (Web Text))

Max Activating Token Index: 583

Text #14

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0272. Min Act: -0.0006

Data Index: 326678 (C4 (Web Text))

Max Activating Token Index: 576

Text #15

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0255. Min Act: -0.0006

Data Index: 96987 (C4 (Web Text))

Max Activating Token Index: 631

Text #16

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0266. Min Act: -0.0006

Data Index: 116425 (C4 (Web Text))

Max Activating Token Index: 842

Text #17

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0271. Min Act: -0.0006

Data Index: 458960 (C4 (Web Text))

Max Activating Token Index: 550

Text #18

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0276. Min Act: -0.0006

Data Index: 1287797 (C4 (Web Text))

Max Activating Token Index: 508

Text #19

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0270. Min Act: -0.0006

Data Index: 1311536 (C4 (Web Text))

Max Activating Token Index: 465