Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1575 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1470. Min Act: -0.0001

Data Index: 308976 (C4 (Web Text))

Max Activating Token Index: 148

Text #1

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1522. Min Act: -0.0001

Data Index: 212209 (C4 (Web Text))

Max Activating Token Index: 151

Text #2

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1461. Min Act: -0.0001

Data Index: 1358558 (C4 (Web Text))

Max Activating Token Index: 390

Text #3

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1428. Min Act: -0.0001

Data Index: 46004 (C4 (Web Text))

Max Activating Token Index: 647

Text #4

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1353. Min Act: -0.0001

Data Index: 954642 (C4 (Web Text))

Max Activating Token Index: 675

Text #5

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1380. Min Act: -0.0001

Data Index: 759614 (C4 (Web Text))

Max Activating Token Index: 664

Text #6

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1331. Min Act: -0.0001

Data Index: 969209 (C4 (Web Text))

Max Activating Token Index: 116

Text #7

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1249. Min Act: -0.0001

Data Index: 1269389 (C4 (Web Text))

Max Activating Token Index: 923

Text #8

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1277. Min Act: -0.0001

Data Index: 780709 (C4 (Web Text))

Max Activating Token Index: 220

Text #9

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1369. Min Act: -0.0001

Data Index: 339306 (C4 (Web Text))

Max Activating Token Index: 480

Text #10

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1325. Min Act: -0.0001

Data Index: 1312835 (C4 (Web Text))

Max Activating Token Index: 104

Text #11

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1312. Min Act: -0.0001

Data Index: 903063 (C4 (Web Text))

Max Activating Token Index: 396

Text #12

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1300. Min Act: -0.0001

Data Index: 607291 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1231. Min Act: -0.0001

Data Index: 1210009 (C4 (Web Text))

Max Activating Token Index: 117

Text #14

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1208. Min Act: -0.0001

Data Index: 716483 (C4 (Web Text))

Max Activating Token Index: 59

Text #15

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1298. Min Act: -0.0001

Data Index: 553628 (C4 (Web Text))

Max Activating Token Index: 977

Text #16

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1346. Min Act: -0.0001

Data Index: 566740 (C4 (Web Text))

Max Activating Token Index: 897

Text #17

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1210. Min Act: -0.0001

Data Index: 395815 (C4 (Web Text))

Max Activating Token Index: 495

Text #18

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1201. Min Act: -0.0001

Data Index: 565045 (C4 (Web Text))

Max Activating Token Index: 877

Text #19

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1288. Min Act: -0.0001

Data Index: 1256644 (C4 (Web Text))

Max Activating Token Index: 59