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

Dataset: The Pile

Neuron 2921 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: 1.2595. Min Range: -1.2595

Max Act: 1.2595. Min Act: -0.0000

Data Index: 1512926 (The Pile)

Max Activating Token Index: 441

Text #1

Max Range: 1.2595. Min Range: -1.2595

Max Act: 1.1086. Min Act: -0.0000

Data Index: 393789 (The Pile)

Max Activating Token Index: 520

Text #2

Max Range: 1.2595. Min Range: -1.2595

Max Act: 0.9933. Min Act: -0.0000

Data Index: 1363337 (The Pile)

Max Activating Token Index: 173

Text #3

Max Range: 1.2595. Min Range: -1.2595

Max Act: 0.9196. Min Act: -0.0000

Data Index: 120557 (The Pile)

Max Activating Token Index: 337

Text #4

Max Range: 1.2595. Min Range: -1.2595

Max Act: 0.9086. Min Act: -0.0000

Data Index: 1487821 (The Pile)

Max Activating Token Index: 220

Text #5

Max Range: 1.2595. Min Range: -1.2595

Max Act: 0.9180. Min Act: -0.0000

Data Index: 1093209 (The Pile)

Max Activating Token Index: 160

Text #6

Max Range: 1.2595. Min Range: -1.2595

Max Act: 0.9204. Min Act: -0.0000

Data Index: 1225773 (The Pile)

Max Activating Token Index: 605

Text #7

Max Range: 1.2595. Min Range: -1.2595

Max Act: 0.8848. Min Act: -0.0000

Data Index: 1590297 (The Pile)

Max Activating Token Index: 479

Text #8

Max Range: 1.2595. Min Range: -1.2595

Max Act: 0.8703. Min Act: -0.0000

Data Index: 1666610 (The Pile)

Max Activating Token Index: 593

Text #9

Max Range: 1.2595. Min Range: -1.2595

Max Act: 0.7886. Min Act: -0.0000

Data Index: 1582829 (The Pile)

Max Activating Token Index: 745

Text #10

Max Range: 1.2595. Min Range: -1.2595

Max Act: 0.8212. Min Act: -0.0000

Data Index: 1607503 (The Pile)

Max Activating Token Index: 328

Text #11

Max Range: 1.2595. Min Range: -1.2595

Max Act: 0.7904. Min Act: -0.0000

Data Index: 225377 (The Pile)

Max Activating Token Index: 926

Text #12

Max Range: 1.2595. Min Range: -1.2595

Max Act: 0.8948. Min Act: -0.0000

Data Index: 315941 (The Pile)

Max Activating Token Index: 674

Text #13

Max Range: 1.2595. Min Range: -1.2595

Max Act: 0.7869. Min Act: -0.0000

Data Index: 1880690 (The Pile)

Max Activating Token Index: 965

Text #14

Max Range: 1.2595. Min Range: -1.2595

Max Act: 0.7576. Min Act: -0.0000

Data Index: 204809 (The Pile)

Max Activating Token Index: 73

Text #15

Max Range: 1.2595. Min Range: -1.2595

Max Act: 0.7814. Min Act: -0.0000

Data Index: 57964 (The Pile)

Max Activating Token Index: 336

Text #16

Max Range: 1.2595. Min Range: -1.2595

Max Act: 0.7232. Min Act: -0.0000

Data Index: 1618054 (The Pile)

Max Activating Token Index: 976

Text #17

Max Range: 1.2595. Min Range: -1.2595

Max Act: 0.7276. Min Act: -0.0000

Data Index: 782763 (The Pile)

Max Activating Token Index: 953

Text #18

Max Range: 1.2595. Min Range: -1.2595

Max Act: 0.7029. Min Act: -0.0000

Data Index: 1158740 (The Pile)

Max Activating Token Index: 614

Text #19

Max Range: 1.2595. Min Range: -1.2595

Max Act: 0.7338. Min Act: -0.0000

Data Index: 1452913 (The Pile)

Max Activating Token Index: 464