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

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

Neuron 3357 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: 0.1877. Min Range: -0.1877

Max Act: 0.1877. Min Act: -0.0001

Data Index: 571783 (C4 (Web Text))

Max Activating Token Index: 806

Text #1

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1549. Min Act: -0.0001

Data Index: 1110765 (C4 (Web Text))

Max Activating Token Index: 393

Text #2

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1565. Min Act: -0.0001

Data Index: 386964 (C4 (Web Text))

Max Activating Token Index: 1020

Text #3

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1499. Min Act: -0.0001

Data Index: 480697 (C4 (Web Text))

Max Activating Token Index: 372

Text #4

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1499. Min Act: -0.0001

Data Index: 63764 (C4 (Web Text))

Max Activating Token Index: 190

Text #5

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1466. Min Act: -0.0001

Data Index: 1294802 (C4 (Web Text))

Max Activating Token Index: 303

Text #6

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1438. Min Act: -0.0001

Data Index: 352683 (C4 (Web Text))

Max Activating Token Index: 256

Text #7

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1446. Min Act: -0.0001

Data Index: 1305000 (C4 (Web Text))

Max Activating Token Index: 205

Text #8

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1431. Min Act: -0.0001

Data Index: 508240 (C4 (Web Text))

Max Activating Token Index: 236

Text #9

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1359. Min Act: -0.0001

Data Index: 533990 (C4 (Web Text))

Max Activating Token Index: 306

Text #10

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1317. Min Act: -0.0001

Data Index: 338973 (C4 (Web Text))

Max Activating Token Index: 430

Text #11

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1358. Min Act: -0.0001

Data Index: 141203 (C4 (Web Text))

Max Activating Token Index: 204

Text #12

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1330. Min Act: -0.0000

Data Index: 1125522 (C4 (Web Text))

Max Activating Token Index: 470

Text #13

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1333. Min Act: -0.0001

Data Index: 494665 (C4 (Web Text))

Max Activating Token Index: 92

Text #14

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1328. Min Act: -0.0001

Data Index: 18745 (C4 (Web Text))

Max Activating Token Index: 173

Text #15

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1312. Min Act: -0.0001

Data Index: 1020650 (C4 (Web Text))

Max Activating Token Index: 176

Text #16

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1295. Min Act: -0.0001

Data Index: 297927 (C4 (Web Text))

Max Activating Token Index: 354

Text #17

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1288. Min Act: -0.0001

Data Index: 505876 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1278. Min Act: -0.0001

Data Index: 41459 (C4 (Web Text))

Max Activating Token Index: 463

Text #19

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1282. Min Act: -0.0001

Data Index: 1223319 (C4 (Web Text))

Max Activating Token Index: 782