Model: SoLU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 512 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.2805. Min Act: -0.0003

Data Index: 1398142 (Python Code)

Max Activating Token Index: 449

Text #1

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.2339. Min Act: -0.0003

Data Index: 1641658 (Python Code)

Max Activating Token Index: 939

Text #2

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.2351. Min Act: -0.0003

Data Index: 1359875 (Python Code)

Max Activating Token Index: 550

Text #3

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.2250. Min Act: -0.0003

Data Index: 1590177 (Python Code)

Max Activating Token Index: 381

Text #4

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.2326. Min Act: -0.0003

Data Index: 1585140 (Python Code)

Max Activating Token Index: 686

Text #5

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.2402. Min Act: -0.0003

Data Index: 1489477 (Python Code)

Max Activating Token Index: 254

Text #6

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.2228. Min Act: -0.0003

Data Index: 1409456 (Python Code)

Max Activating Token Index: 350

Text #7

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.2270. Min Act: -0.0003

Data Index: 1501391 (Python Code)

Max Activating Token Index: 592

Text #8

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.2204. Min Act: -0.0003

Data Index: 1434840 (Python Code)

Max Activating Token Index: 202

Text #9

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.2200. Min Act: -0.0003

Data Index: 1453297 (Python Code)

Max Activating Token Index: 103

Text #10

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.2224. Min Act: -0.0003

Data Index: 1426434 (Python Code)

Max Activating Token Index: 485

Text #11

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.2168. Min Act: -0.0003

Data Index: 1553656 (Python Code)

Max Activating Token Index: 240

Text #12

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.2171. Min Act: -0.0003

Data Index: 1544094 (Python Code)

Max Activating Token Index: 33

Text #13

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.2165. Min Act: -0.0003

Data Index: 1576979 (Python Code)

Max Activating Token Index: 734

Text #14

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.2122. Min Act: -0.0003

Data Index: 1418103 (Python Code)

Max Activating Token Index: 1001

Text #15

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.2064. Min Act: -0.0003

Data Index: 1403560 (Python Code)

Max Activating Token Index: 578

Text #16

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.2093. Min Act: -0.0003

Data Index: 1564702 (Python Code)

Max Activating Token Index: 859

Text #17

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.2042. Min Act: -0.0003

Data Index: 1447837 (Python Code)

Max Activating Token Index: 690

Text #18

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.2095. Min Act: -0.0003

Data Index: 1568080 (Python Code)

Max Activating Token Index: 913

Text #19

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.2011. Min Act: -0.0003

Data Index: 1647411 (Python Code)

Max Activating Token Index: 802