Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2476 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.6440. Min Act: -0.0000

Data Index: 1816857 (The Pile)

Max Activating Token Index: 679

Text #1

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.6599. Min Act: -0.0000

Data Index: 1870936 (The Pile)

Max Activating Token Index: 824

Text #2

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.6366. Min Act: -0.0000

Data Index: 1231568 (The Pile)

Max Activating Token Index: 68

Text #3

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.6115. Min Act: -0.0000

Data Index: 216013 (The Pile)

Max Activating Token Index: 83

Text #4

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.5554. Min Act: -0.0000

Data Index: 1531018 (The Pile)

Max Activating Token Index: 922

Text #5

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.5089. Min Act: -0.0000

Data Index: 64363 (The Pile)

Max Activating Token Index: 700

Text #6

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.5052. Min Act: -0.0000

Data Index: 690580 (The Pile)

Max Activating Token Index: 1005

Text #7

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.4938. Min Act: -0.0000

Data Index: 1834740 (The Pile)

Max Activating Token Index: 633

Text #8

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.5170. Min Act: -0.0000

Data Index: 258993 (The Pile)

Max Activating Token Index: 345

Text #9

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.4919. Min Act: -0.0000

Data Index: 38910 (The Pile)

Max Activating Token Index: 422

Text #10

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.4612. Min Act: -0.0000

Data Index: 1851921 (The Pile)

Max Activating Token Index: 537

Text #11

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.4799. Min Act: -0.0000

Data Index: 1871263 (The Pile)

Max Activating Token Index: 580

Text #12

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.5004. Min Act: -0.0000

Data Index: 1547136 (The Pile)

Max Activating Token Index: 88

Text #13

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.4922. Min Act: -0.0000

Data Index: 1948198 (The Pile)

Max Activating Token Index: 225

Text #14

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.4405. Min Act: -0.0000

Data Index: 923759 (The Pile)

Max Activating Token Index: 401

Text #15

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.4561. Min Act: -0.0000

Data Index: 375967 (The Pile)

Max Activating Token Index: 390

Text #16

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.4467. Min Act: -0.0000

Data Index: 322928 (The Pile)

Max Activating Token Index: 565

Text #17

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.4304. Min Act: -0.0000

Data Index: 1028217 (The Pile)

Max Activating Token Index: 471

Text #18

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.4326. Min Act: -0.0000

Data Index: 1277092 (The Pile)

Max Activating Token Index: 482

Text #19

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.4585. Min Act: -0.0000

Data Index: 207052 (The Pile)

Max Activating Token Index: 941