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

Dataset: The Pile

Neuron 4452 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1586. Min Act: 0.0000

Data Index: 1280714 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1482. Min Act: -0.0000

Data Index: 903979 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1481. Min Act: -0.0000

Data Index: 938109 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1380. Min Act: 0.0000

Data Index: 1875329 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1362. Min Act: -0.0000

Data Index: 501510 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1287. Min Act: 0.0000

Data Index: 1212261 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1270. Min Act: -0.0000

Data Index: 65638 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1259. Min Act: 0.0000

Data Index: 664830 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1215. Min Act: 0.0000

Data Index: 267884 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1242. Min Act: 0.0000

Data Index: 680993 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1226. Min Act: -0.0000

Data Index: 1205410 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1186. Min Act: -0.0000

Data Index: 394927 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1184. Min Act: 0.0000

Data Index: 949756 (The Pile)

Max Activating Token Index: 84

Text #13

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1180. Min Act: 0.0000

Data Index: 280853 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1177. Min Act: 0.0000

Data Index: 1783947 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1174. Min Act: 0.0000

Data Index: 18290 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1168. Min Act: -0.0000

Data Index: 1123813 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1156. Min Act: 0.0000

Data Index: 441608 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1140. Min Act: -0.0000

Data Index: 499720 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1141. Min Act: -0.0000

Data Index: 651783 (The Pile)

Max Activating Token Index: 50