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

Dataset: The Pile

Neuron 3587 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1226. Min Act: -0.0000

Data Index: 1512392 (The Pile)

Max Activating Token Index: 346

Text #1

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1145. Min Act: -0.0000

Data Index: 562619 (The Pile)

Max Activating Token Index: 339

Text #2

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1260. Min Act: -0.0000

Data Index: 561999 (The Pile)

Max Activating Token Index: 105

Text #3

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1177. Min Act: -0.0000

Data Index: 154161 (The Pile)

Max Activating Token Index: 154

Text #4

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1086. Min Act: -0.0000

Data Index: 1867541 (The Pile)

Max Activating Token Index: 217

Text #5

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0990. Min Act: -0.0000

Data Index: 1493761 (The Pile)

Max Activating Token Index: 500

Text #6

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1100. Min Act: -0.0000

Data Index: 1316402 (The Pile)

Max Activating Token Index: 671

Text #7

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1128. Min Act: -0.0000

Data Index: 1107501 (The Pile)

Max Activating Token Index: 282

Text #8

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1006. Min Act: -0.0000

Data Index: 317401 (The Pile)

Max Activating Token Index: 454

Text #9

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1075. Min Act: -0.0000

Data Index: 1791534 (The Pile)

Max Activating Token Index: 438

Text #10

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0978. Min Act: -0.0000

Data Index: 1237657 (The Pile)

Max Activating Token Index: 290

Text #11

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0933. Min Act: -0.0000

Data Index: 1947906 (The Pile)

Max Activating Token Index: 604

Text #12

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0892. Min Act: -0.0000

Data Index: 425086 (The Pile)

Max Activating Token Index: 35

Text #13

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0937. Min Act: -0.0000

Data Index: 1242198 (The Pile)

Max Activating Token Index: 356

Text #14

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0908. Min Act: -0.0000

Data Index: 1177872 (The Pile)

Max Activating Token Index: 543

Text #15

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0734. Min Act: -0.0000

Data Index: 863985 (The Pile)

Max Activating Token Index: 133

Text #16

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0901. Min Act: -0.0000

Data Index: 1359262 (The Pile)

Max Activating Token Index: 33

Text #17

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0870. Min Act: -0.0000

Data Index: 380976 (The Pile)

Max Activating Token Index: 73

Text #18

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0956. Min Act: -0.0000

Data Index: 1863380 (The Pile)

Max Activating Token Index: 117

Text #19

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0825. Min Act: -0.0000

Data Index: 1338232 (The Pile)

Max Activating Token Index: 324