Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1691 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2963. Min Range: -1.2963

Max Act: 1.2963. Min Act: -0.0000

Data Index: 376531 (C4 (Web Text))

Max Activating Token Index: 504

Text #1

Max Range: 1.2963. Min Range: -1.2963

Max Act: 1.1027. Min Act: -0.0000

Data Index: 314216 (C4 (Web Text))

Max Activating Token Index: 607

Text #2

Max Range: 1.2963. Min Range: -1.2963

Max Act: 1.0546. Min Act: -0.0000

Data Index: 245938 (C4 (Web Text))

Max Activating Token Index: 850

Text #3

Max Range: 1.2963. Min Range: -1.2963

Max Act: 0.9630. Min Act: -0.0000

Data Index: 263922 (C4 (Web Text))

Max Activating Token Index: 635

Text #4

Max Range: 1.2963. Min Range: -1.2963

Max Act: 0.9428. Min Act: -0.0000

Data Index: 471106 (C4 (Web Text))

Max Activating Token Index: 786

Text #5

Max Range: 1.2963. Min Range: -1.2963

Max Act: 1.0060. Min Act: -0.0000

Data Index: 186748 (C4 (Web Text))

Max Activating Token Index: 86

Text #6

Max Range: 1.2963. Min Range: -1.2963

Max Act: 1.0258. Min Act: -0.0000

Data Index: 539273 (C4 (Web Text))

Max Activating Token Index: 1008

Text #7

Max Range: 1.2963. Min Range: -1.2963

Max Act: 0.9660. Min Act: -0.0000

Data Index: 575772 (C4 (Web Text))

Max Activating Token Index: 760

Text #8

Max Range: 1.2963. Min Range: -1.2963

Max Act: 0.9761. Min Act: -0.0000

Data Index: 1100061 (C4 (Web Text))

Max Activating Token Index: 781

Text #9

Max Range: 1.2963. Min Range: -1.2963

Max Act: 0.8058. Min Act: -0.0000

Data Index: 808485 (C4 (Web Text))

Max Activating Token Index: 974

Text #10

Max Range: 1.2963. Min Range: -1.2963

Max Act: 0.8994. Min Act: -0.0000

Data Index: 72456 (C4 (Web Text))

Max Activating Token Index: 332

Text #11

Max Range: 1.2963. Min Range: -1.2963

Max Act: 0.8897. Min Act: -0.0000

Data Index: 356577 (C4 (Web Text))

Max Activating Token Index: 777

Text #12

Max Range: 1.2963. Min Range: -1.2963

Max Act: 0.8292. Min Act: -0.0000

Data Index: 256217 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 1.2963. Min Range: -1.2963

Max Act: 0.8735. Min Act: -0.0000

Data Index: 1260688 (C4 (Web Text))

Max Activating Token Index: 256

Text #14

Max Range: 1.2963. Min Range: -1.2963

Max Act: 0.8672. Min Act: -0.0000

Data Index: 919155 (C4 (Web Text))

Max Activating Token Index: 1015

Text #15

Max Range: 1.2963. Min Range: -1.2963

Max Act: 0.8568. Min Act: -0.0000

Data Index: 1003195 (C4 (Web Text))

Max Activating Token Index: 471

Text #16

Max Range: 1.2963. Min Range: -1.2963

Max Act: 0.8399. Min Act: -0.0000

Data Index: 137209 (C4 (Web Text))

Max Activating Token Index: 484

Text #17

Max Range: 1.2963. Min Range: -1.2963

Max Act: 0.8831. Min Act: -0.0000

Data Index: 691148 (C4 (Web Text))

Max Activating Token Index: 256

Text #18

Max Range: 1.2963. Min Range: -1.2963

Max Act: 0.8821. Min Act: -0.0000

Data Index: 92268 (C4 (Web Text))

Max Activating Token Index: 569

Text #19

Max Range: 1.2963. Min Range: -1.2963

Max Act: 0.8304. Min Act: -0.0000

Data Index: 1272223 (C4 (Web Text))

Max Activating Token Index: 22