Model: SoLU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 625 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0422. Min Act: -0.0003

Data Index: 528365 (C4 (Web Text))

Max Activating Token Index: 191

Text #1

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0362. Min Act: -0.0003

Data Index: 1221099 (C4 (Web Text))

Max Activating Token Index: 664

Text #2

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0352. Min Act: -0.0003

Data Index: 1518997 (Python Code)

Max Activating Token Index: 815

Text #3

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0356. Min Act: -0.0003

Data Index: 1550968 (Python Code)

Max Activating Token Index: 300

Text #4

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0347. Min Act: -0.0003

Data Index: 1555745 (Python Code)

Max Activating Token Index: 696

Text #5

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0331. Min Act: -0.0004

Data Index: 1374276 (Python Code)

Max Activating Token Index: 550

Text #6

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0328. Min Act: -0.0003

Data Index: 1010413 (C4 (Web Text))

Max Activating Token Index: 864

Text #7

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0301. Min Act: -0.0003

Data Index: 1600993 (Python Code)

Max Activating Token Index: 511

Text #8

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0304. Min Act: -0.0003

Data Index: 1519790 (Python Code)

Max Activating Token Index: 893

Text #9

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0304. Min Act: -0.0003

Data Index: 306424 (C4 (Web Text))

Max Activating Token Index: 414

Text #10

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0301. Min Act: -0.0003

Data Index: 1464952 (Python Code)

Max Activating Token Index: 353

Text #11

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0296. Min Act: -0.0003

Data Index: 1622582 (Python Code)

Max Activating Token Index: 107

Text #12

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0301. Min Act: -0.0003

Data Index: 1419473 (Python Code)

Max Activating Token Index: 763

Text #13

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0292. Min Act: -0.0003

Data Index: 569072 (C4 (Web Text))

Max Activating Token Index: 695

Text #14

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0286. Min Act: -0.0003

Data Index: 800272 (C4 (Web Text))

Max Activating Token Index: 246

Text #15

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0284. Min Act: -0.0003

Data Index: 1378731 (Python Code)

Max Activating Token Index: 10

Text #16

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0284. Min Act: -0.0003

Data Index: 1372064 (Python Code)

Max Activating Token Index: 73

Text #17

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0278. Min Act: -0.0003

Data Index: 643477 (C4 (Web Text))

Max Activating Token Index: 235

Text #18

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0281. Min Act: -0.0003

Data Index: 946766 (C4 (Web Text))

Max Activating Token Index: 347

Text #19

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0281. Min Act: -0.0003

Data Index: 1390405 (Python Code)

Max Activating Token Index: 722