Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2023 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1536. Min Act: -0.0001

Data Index: 150283 (C4 (Web Text))

Max Activating Token Index: 12

Text #1

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1466. Min Act: -0.0001

Data Index: 643945 (C4 (Web Text))

Max Activating Token Index: 2

Text #2

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1375. Min Act: -0.0001

Data Index: 7371 (C4 (Web Text))

Max Activating Token Index: 2

Text #3

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1379. Min Act: -0.0001

Data Index: 886519 (C4 (Web Text))

Max Activating Token Index: 301

Text #4

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1485. Min Act: -0.0001

Data Index: 1287653 (C4 (Web Text))

Max Activating Token Index: 77

Text #5

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1314. Min Act: -0.0001

Data Index: 998630 (C4 (Web Text))

Max Activating Token Index: 847

Text #6

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1349. Min Act: -0.0001

Data Index: 42721 (C4 (Web Text))

Max Activating Token Index: 813

Text #7

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1333. Min Act: -0.0001

Data Index: 401989 (C4 (Web Text))

Max Activating Token Index: 3

Text #8

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1374. Min Act: -0.0001

Data Index: 19593 (C4 (Web Text))

Max Activating Token Index: 3

Text #9

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1309. Min Act: -0.0001

Data Index: 115834 (C4 (Web Text))

Max Activating Token Index: 7

Text #10

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1256. Min Act: -0.0001

Data Index: 251061 (C4 (Web Text))

Max Activating Token Index: 541

Text #11

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1312. Min Act: -0.0001

Data Index: 95009 (C4 (Web Text))

Max Activating Token Index: 235

Text #12

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1296. Min Act: -0.0001

Data Index: 1785 (C4 (Web Text))

Max Activating Token Index: 605

Text #13

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1347. Min Act: -0.0001

Data Index: 301041 (C4 (Web Text))

Max Activating Token Index: 342

Text #14

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1260. Min Act: -0.0001

Data Index: 96823 (C4 (Web Text))

Max Activating Token Index: 545

Text #15

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1088. Min Act: -0.0001

Data Index: 1085740 (C4 (Web Text))

Max Activating Token Index: 72

Text #16

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1288. Min Act: -0.0001

Data Index: 1083364 (C4 (Web Text))

Max Activating Token Index: 722

Text #17

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1145. Min Act: -0.0001

Data Index: 44726 (C4 (Web Text))

Max Activating Token Index: 64

Text #18

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1142. Min Act: -0.0001

Data Index: 23085 (C4 (Web Text))

Max Activating Token Index: 767

Text #19

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1169. Min Act: -0.0001

Data Index: 732800 (C4 (Web Text))

Max Activating Token Index: 630