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

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

Neuron 5244 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0359. Min Act: -0.0001

Data Index: 416677 (C4 (Web Text))

Max Activating Token Index: 340

Text #1

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0362. Min Act: -0.0001

Data Index: 603488 (C4 (Web Text))

Max Activating Token Index: 364

Text #2

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0347. Min Act: -0.0001

Data Index: 1094925 (C4 (Web Text))

Max Activating Token Index: 720

Text #3

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0349. Min Act: -0.0001

Data Index: 889850 (C4 (Web Text))

Max Activating Token Index: 260

Text #4

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0352. Min Act: -0.0001

Data Index: 841812 (C4 (Web Text))

Max Activating Token Index: 765

Text #5

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0353. Min Act: -0.0001

Data Index: 1228358 (C4 (Web Text))

Max Activating Token Index: 548

Text #6

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0341. Min Act: -0.0001

Data Index: 253621 (C4 (Web Text))

Max Activating Token Index: 627

Text #7

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0342. Min Act: -0.0001

Data Index: 1030672 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0340. Min Act: -0.0001

Data Index: 1035392 (C4 (Web Text))

Max Activating Token Index: 153

Text #9

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0346. Min Act: -0.0001

Data Index: 128465 (C4 (Web Text))

Max Activating Token Index: 176

Text #10

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0333. Min Act: -0.0001

Data Index: 1339384 (C4 (Web Text))

Max Activating Token Index: 365

Text #11

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0337. Min Act: -0.0001

Data Index: 331608 (C4 (Web Text))

Max Activating Token Index: 33

Text #12

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0327. Min Act: -0.0001

Data Index: 443116 (C4 (Web Text))

Max Activating Token Index: 440

Text #13

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0330. Min Act: -0.0001

Data Index: 163434 (C4 (Web Text))

Max Activating Token Index: 364

Text #14

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0326. Min Act: -0.0001

Data Index: 321640 (C4 (Web Text))

Max Activating Token Index: 338

Text #15

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0328. Min Act: -0.0001

Data Index: 1358459 (C4 (Web Text))

Max Activating Token Index: 5

Text #16

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0330. Min Act: -0.0001

Data Index: 1350634 (C4 (Web Text))

Max Activating Token Index: 215

Text #17

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0326. Min Act: -0.0001

Data Index: 891335 (C4 (Web Text))

Max Activating Token Index: 668

Text #18

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0323. Min Act: -0.0001

Data Index: 1296690 (C4 (Web Text))

Max Activating Token Index: 904

Text #19

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0330. Min Act: -0.0001

Data Index: 1241651 (C4 (Web Text))

Max Activating Token Index: 561