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

Dataset: The Pile

Neuron 958 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3161. Min Range: -1.3161

Max Act: 1.3161. Min Act: -0.0000

Data Index: 1677813 (The Pile)

Max Activating Token Index: 421

Text #1

Max Range: 1.3161. Min Range: -1.3161

Max Act: 1.1217. Min Act: -0.0000

Data Index: 332422 (The Pile)

Max Activating Token Index: 470

Text #2

Max Range: 1.3161. Min Range: -1.3161

Max Act: 1.0570. Min Act: -0.0000

Data Index: 1043433 (The Pile)

Max Activating Token Index: 387

Text #3

Max Range: 1.3161. Min Range: -1.3161

Max Act: 1.0177. Min Act: -0.0000

Data Index: 1860835 (The Pile)

Max Activating Token Index: 487

Text #4

Max Range: 1.3161. Min Range: -1.3161

Max Act: 0.9160. Min Act: -0.0000

Data Index: 120379 (The Pile)

Max Activating Token Index: 817

Text #5

Max Range: 1.3161. Min Range: -1.3161

Max Act: 0.9496. Min Act: -0.0000

Data Index: 454938 (The Pile)

Max Activating Token Index: 501

Text #6

Max Range: 1.3161. Min Range: -1.3161

Max Act: 0.8973. Min Act: -0.0000

Data Index: 1939469 (The Pile)

Max Activating Token Index: 949

Text #7

Max Range: 1.3161. Min Range: -1.3161

Max Act: 0.9156. Min Act: 0.0000

Data Index: 994652 (The Pile)

Max Activating Token Index: 766

Text #8

Max Range: 1.3161. Min Range: -1.3161

Max Act: 0.8426. Min Act: -0.0000

Data Index: 1050300 (The Pile)

Max Activating Token Index: 578

Text #9

Max Range: 1.3161. Min Range: -1.3161

Max Act: 0.9127. Min Act: -0.0000

Data Index: 833481 (The Pile)

Max Activating Token Index: 127

Text #10

Max Range: 1.3161. Min Range: -1.3161

Max Act: 0.8729. Min Act: -0.0000

Data Index: 382688 (The Pile)

Max Activating Token Index: 491

Text #11

Max Range: 1.3161. Min Range: -1.3161

Max Act: 0.9492. Min Act: -0.0000

Data Index: 1243577 (The Pile)

Max Activating Token Index: 186

Text #12

Max Range: 1.3161. Min Range: -1.3161

Max Act: 0.8684. Min Act: -0.0000

Data Index: 1094331 (The Pile)

Max Activating Token Index: 166

Text #13

Max Range: 1.3161. Min Range: -1.3161

Max Act: 0.8499. Min Act: -0.0000

Data Index: 779776 (The Pile)

Max Activating Token Index: 224

Text #14

Max Range: 1.3161. Min Range: -1.3161

Max Act: 0.8253. Min Act: -0.0000

Data Index: 43467 (The Pile)

Max Activating Token Index: 528

Text #15

Max Range: 1.3161. Min Range: -1.3161

Max Act: 0.8542. Min Act: 0.0000

Data Index: 1863402 (The Pile)

Max Activating Token Index: 196

Text #16

Max Range: 1.3161. Min Range: -1.3161

Max Act: 0.8099. Min Act: -0.0000

Data Index: 817986 (The Pile)

Max Activating Token Index: 226

Text #17

Max Range: 1.3161. Min Range: -1.3161

Max Act: 0.8088. Min Act: -0.0000

Data Index: 505296 (The Pile)

Max Activating Token Index: 748

Text #18

Max Range: 1.3161. Min Range: -1.3161

Max Act: 0.8553. Min Act: -0.0000

Data Index: 1368775 (The Pile)

Max Activating Token Index: 129

Text #19

Max Range: 1.3161. Min Range: -1.3161

Max Act: 0.8250. Min Act: -0.0000

Data Index: 692136 (The Pile)

Max Activating Token Index: 664