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

Dataset: The Pile

Neuron 2276 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1520. Min Act: -0.0000

Data Index: 967977 (The Pile)

Max Activating Token Index: 874

Text #1

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1425. Min Act: -0.0000

Data Index: 1106244 (The Pile)

Max Activating Token Index: 885

Text #2

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1385. Min Act: -0.0000

Data Index: 1191245 (The Pile)

Max Activating Token Index: 97

Text #3

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1385. Min Act: -0.0000

Data Index: 817430 (The Pile)

Max Activating Token Index: 815

Text #4

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1369. Min Act: -0.0000

Data Index: 1860182 (The Pile)

Max Activating Token Index: 771

Text #5

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1318. Min Act: -0.0000

Data Index: 1828310 (The Pile)

Max Activating Token Index: 934

Text #6

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1327. Min Act: -0.0000

Data Index: 1463763 (The Pile)

Max Activating Token Index: 390

Text #7

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1289. Min Act: -0.0000

Data Index: 1406763 (The Pile)

Max Activating Token Index: 358

Text #8

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1419. Min Act: -0.0000

Data Index: 1162122 (The Pile)

Max Activating Token Index: 691

Text #9

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1336. Min Act: -0.0000

Data Index: 1815638 (The Pile)

Max Activating Token Index: 147

Text #10

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1344. Min Act: -0.0000

Data Index: 1617119 (The Pile)

Max Activating Token Index: 924

Text #11

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1198. Min Act: -0.0000

Data Index: 1461458 (The Pile)

Max Activating Token Index: 736

Text #12

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1110. Min Act: 0.0000

Data Index: 1986202 (The Pile)

Max Activating Token Index: 907

Text #13

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1262. Min Act: -0.0000

Data Index: 1193778 (The Pile)

Max Activating Token Index: 1017

Text #14

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1323. Min Act: -0.0000

Data Index: 1146521 (The Pile)

Max Activating Token Index: 825

Text #15

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1241. Min Act: -0.0000

Data Index: 726902 (The Pile)

Max Activating Token Index: 900

Text #16

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1141. Min Act: -0.0000

Data Index: 754698 (The Pile)

Max Activating Token Index: 1000

Text #17

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1118. Min Act: -0.0000

Data Index: 1284299 (The Pile)

Max Activating Token Index: 632

Text #18

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1146. Min Act: -0.0000

Data Index: 1437788 (The Pile)

Max Activating Token Index: 558

Text #19

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1273. Min Act: -0.0000

Data Index: 957485 (The Pile)

Max Activating Token Index: 524