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

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

Neuron 4524 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1941. Min Range: -0.1941

Max Act: 0.1941. Min Act: -0.0000

Data Index: 353700 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 0.1941. Min Range: -0.1941

Max Act: 0.1643. Min Act: -0.0000

Data Index: 344183 (C4 (Web Text))

Max Activating Token Index: 10

Text #2

Max Range: 0.1941. Min Range: -0.1941

Max Act: 0.1559. Min Act: -0.0000

Data Index: 1245449 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 0.1941. Min Range: -0.1941

Max Act: 0.1380. Min Act: -0.0000

Data Index: 43759 (C4 (Web Text))

Max Activating Token Index: 848

Text #4

Max Range: 0.1941. Min Range: -0.1941

Max Act: 0.1544. Min Act: -0.0000

Data Index: 1187992 (C4 (Web Text))

Max Activating Token Index: 765

Text #5

Max Range: 0.1941. Min Range: -0.1941

Max Act: 0.1512. Min Act: -0.0000

Data Index: 228537 (C4 (Web Text))

Max Activating Token Index: 722

Text #6

Max Range: 0.1941. Min Range: -0.1941

Max Act: 0.1439. Min Act: -0.0000

Data Index: 1032336 (C4 (Web Text))

Max Activating Token Index: 512

Text #7

Max Range: 0.1941. Min Range: -0.1941

Max Act: 0.1310. Min Act: -0.0000

Data Index: 600908 (C4 (Web Text))

Max Activating Token Index: 211

Text #8

Max Range: 0.1941. Min Range: -0.1941

Max Act: 0.1372. Min Act: -0.0000

Data Index: 471661 (C4 (Web Text))

Max Activating Token Index: 395

Text #9

Max Range: 0.1941. Min Range: -0.1941

Max Act: 0.1397. Min Act: -0.0000

Data Index: 672290 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 0.1941. Min Range: -0.1941

Max Act: 0.1367. Min Act: -0.0000

Data Index: 1030305 (C4 (Web Text))

Max Activating Token Index: 920

Text #11

Max Range: 0.1941. Min Range: -0.1941

Max Act: 0.1299. Min Act: -0.0000

Data Index: 699744 (C4 (Web Text))

Max Activating Token Index: 11

Text #12

Max Range: 0.1941. Min Range: -0.1941

Max Act: 0.1302. Min Act: -0.0000

Data Index: 572722 (C4 (Web Text))

Max Activating Token Index: 933

Text #13

Max Range: 0.1941. Min Range: -0.1941

Max Act: 0.1330. Min Act: -0.0000

Data Index: 1238348 (C4 (Web Text))

Max Activating Token Index: 916

Text #14

Max Range: 0.1941. Min Range: -0.1941

Max Act: 0.1225. Min Act: -0.0000

Data Index: 1044216 (C4 (Web Text))

Max Activating Token Index: 11

Text #15

Max Range: 0.1941. Min Range: -0.1941

Max Act: 0.1271. Min Act: -0.0000

Data Index: 855365 (C4 (Web Text))

Max Activating Token Index: 578

Text #16

Max Range: 0.1941. Min Range: -0.1941

Max Act: 0.1129. Min Act: -0.0000

Data Index: 1263441 (C4 (Web Text))

Max Activating Token Index: 982

Text #17

Max Range: 0.1941. Min Range: -0.1941

Max Act: 0.1302. Min Act: -0.0000

Data Index: 457518 (C4 (Web Text))

Max Activating Token Index: 46

Text #18

Max Range: 0.1941. Min Range: -0.1941

Max Act: 0.1246. Min Act: -0.0000

Data Index: 716073 (C4 (Web Text))

Max Activating Token Index: 1019

Text #19

Max Range: 0.1941. Min Range: -0.1941

Max Act: 0.1212. Min Act: -0.0000

Data Index: 1026382 (C4 (Web Text))

Max Activating Token Index: 950