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

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

Neuron 4309 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: 0.7920. Min Range: -0.7920

Max Act: 0.7920. Min Act: -0.0000

Data Index: 502146 (C4 (Web Text))

Max Activating Token Index: 925

Text #1

Max Range: 0.7920. Min Range: -0.7920

Max Act: 0.7341. Min Act: -0.0000

Data Index: 930169 (C4 (Web Text))

Max Activating Token Index: 967

Text #2

Max Range: 0.7920. Min Range: -0.7920

Max Act: 0.7293. Min Act: -0.0000

Data Index: 787803 (C4 (Web Text))

Max Activating Token Index: 706

Text #3

Max Range: 0.7920. Min Range: -0.7920

Max Act: 0.7395. Min Act: -0.0000

Data Index: 371084 (C4 (Web Text))

Max Activating Token Index: 683

Text #4

Max Range: 0.7920. Min Range: -0.7920

Max Act: 0.6763. Min Act: -0.0000

Data Index: 472939 (C4 (Web Text))

Max Activating Token Index: 672

Text #5

Max Range: 0.7920. Min Range: -0.7920

Max Act: 0.6454. Min Act: -0.0000

Data Index: 697646 (C4 (Web Text))

Max Activating Token Index: 734

Text #6

Max Range: 0.7920. Min Range: -0.7920

Max Act: 0.6467. Min Act: -0.0000

Data Index: 1150303 (C4 (Web Text))

Max Activating Token Index: 495

Text #7

Max Range: 0.7920. Min Range: -0.7920

Max Act: 0.6344. Min Act: -0.0000

Data Index: 71180 (C4 (Web Text))

Max Activating Token Index: 919

Text #8

Max Range: 0.7920. Min Range: -0.7920

Max Act: 0.5692. Min Act: -0.0000

Data Index: 1290016 (C4 (Web Text))

Max Activating Token Index: 326

Text #9

Max Range: 0.7920. Min Range: -0.7920

Max Act: 0.5966. Min Act: -0.0000

Data Index: 113483 (C4 (Web Text))

Max Activating Token Index: 1004

Text #10

Max Range: 0.7920. Min Range: -0.7920

Max Act: 0.5565. Min Act: -0.0000

Data Index: 1017484 (C4 (Web Text))

Max Activating Token Index: 1010

Text #11

Max Range: 0.7920. Min Range: -0.7920

Max Act: 0.5897. Min Act: -0.0000

Data Index: 95156 (C4 (Web Text))

Max Activating Token Index: 289

Text #12

Max Range: 0.7920. Min Range: -0.7920

Max Act: 0.5088. Min Act: -0.0000

Data Index: 144053 (C4 (Web Text))

Max Activating Token Index: 834

Text #13

Max Range: 0.7920. Min Range: -0.7920

Max Act: 0.5818. Min Act: -0.0000

Data Index: 276060 (C4 (Web Text))

Max Activating Token Index: 1013

Text #14

Max Range: 0.7920. Min Range: -0.7920

Max Act: 0.5828. Min Act: -0.0000

Data Index: 788784 (C4 (Web Text))

Max Activating Token Index: 458

Text #15

Max Range: 0.7920. Min Range: -0.7920

Max Act: 0.5523. Min Act: -0.0000

Data Index: 426511 (C4 (Web Text))

Max Activating Token Index: 544

Text #16

Max Range: 0.7920. Min Range: -0.7920

Max Act: 0.5546. Min Act: -0.0000

Data Index: 939128 (C4 (Web Text))

Max Activating Token Index: 659

Text #17

Max Range: 0.7920. Min Range: -0.7920

Max Act: 0.5808. Min Act: -0.0000

Data Index: 22733 (C4 (Web Text))

Max Activating Token Index: 800

Text #18

Max Range: 0.7920. Min Range: -0.7920

Max Act: 0.5247. Min Act: -0.0000

Data Index: 233762 (C4 (Web Text))

Max Activating Token Index: 651

Text #19

Max Range: 0.7920. Min Range: -0.7920

Max Act: 0.5047. Min Act: -0.0000

Data Index: 873615 (C4 (Web Text))

Max Activating Token Index: 266