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

Dataset: The Pile

Neuron 4111 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: 1.1284. Min Range: -1.1284

Max Act: 1.1284. Min Act: -0.0000

Data Index: 666887 (The Pile)

Max Activating Token Index: 659

Text #1

Max Range: 1.1284. Min Range: -1.1284

Max Act: 1.0463. Min Act: -0.0000

Data Index: 1478026 (The Pile)

Max Activating Token Index: 457

Text #2

Max Range: 1.1284. Min Range: -1.1284

Max Act: 1.0409. Min Act: -0.0000

Data Index: 1397446 (The Pile)

Max Activating Token Index: 189

Text #3

Max Range: 1.1284. Min Range: -1.1284

Max Act: 1.0529. Min Act: -0.0000

Data Index: 331684 (The Pile)

Max Activating Token Index: 220

Text #4

Max Range: 1.1284. Min Range: -1.1284

Max Act: 1.0402. Min Act: -0.0000

Data Index: 859440 (The Pile)

Max Activating Token Index: 100

Text #5

Max Range: 1.1284. Min Range: -1.1284

Max Act: 0.9847. Min Act: -0.0000

Data Index: 1602538 (The Pile)

Max Activating Token Index: 52

Text #6

Max Range: 1.1284. Min Range: -1.1284

Max Act: 0.9560. Min Act: -0.0000

Data Index: 1043071 (The Pile)

Max Activating Token Index: 511

Text #7

Max Range: 1.1284. Min Range: -1.1284

Max Act: 0.9502. Min Act: -0.0000

Data Index: 504075 (The Pile)

Max Activating Token Index: 66

Text #8

Max Range: 1.1284. Min Range: -1.1284

Max Act: 1.0102. Min Act: -0.0000

Data Index: 167968 (The Pile)

Max Activating Token Index: 99

Text #9

Max Range: 1.1284. Min Range: -1.1284

Max Act: 0.8901. Min Act: -0.0000

Data Index: 114831 (The Pile)

Max Activating Token Index: 363

Text #10

Max Range: 1.1284. Min Range: -1.1284

Max Act: 0.9814. Min Act: -0.0000

Data Index: 514516 (The Pile)

Max Activating Token Index: 56

Text #11

Max Range: 1.1284. Min Range: -1.1284

Max Act: 0.9647. Min Act: -0.0000

Data Index: 1945601 (The Pile)

Max Activating Token Index: 416

Text #12

Max Range: 1.1284. Min Range: -1.1284

Max Act: 0.9971. Min Act: -0.0000

Data Index: 998497 (The Pile)

Max Activating Token Index: 857

Text #13

Max Range: 1.1284. Min Range: -1.1284

Max Act: 0.9013. Min Act: -0.0000

Data Index: 1247712 (The Pile)

Max Activating Token Index: 307

Text #14

Max Range: 1.1284. Min Range: -1.1284

Max Act: 0.9272. Min Act: -0.0000

Data Index: 1042277 (The Pile)

Max Activating Token Index: 24

Text #15

Max Range: 1.1284. Min Range: -1.1284

Max Act: 0.9066. Min Act: -0.0000

Data Index: 825733 (The Pile)

Max Activating Token Index: 189

Text #16

Max Range: 1.1284. Min Range: -1.1284

Max Act: 0.8672. Min Act: -0.0000

Data Index: 667883 (The Pile)

Max Activating Token Index: 305

Text #17

Max Range: 1.1284. Min Range: -1.1284

Max Act: 0.9160. Min Act: -0.0000

Data Index: 583793 (The Pile)

Max Activating Token Index: 322

Text #18

Max Range: 1.1284. Min Range: -1.1284

Max Act: 0.9136. Min Act: -0.0000

Data Index: 150859 (The Pile)

Max Activating Token Index: 30

Text #19

Max Range: 1.1284. Min Range: -1.1284

Max Act: 0.8775. Min Act: -0.0000

Data Index: 34307 (The Pile)

Max Activating Token Index: 21