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

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

Neuron 2922 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4930. Min Range: -1.4930

Max Act: 1.4930. Min Act: -0.0000

Data Index: 1063486 (C4 (Web Text))

Max Activating Token Index: 334

Text #1

Max Range: 1.4930. Min Range: -1.4930

Max Act: 1.4445. Min Act: -0.0000

Data Index: 634537 (C4 (Web Text))

Max Activating Token Index: 992

Text #2

Max Range: 1.4930. Min Range: -1.4930

Max Act: 1.3843. Min Act: -0.0000

Data Index: 382000 (C4 (Web Text))

Max Activating Token Index: 476

Text #3

Max Range: 1.4930. Min Range: -1.4930

Max Act: 1.4163. Min Act: -0.0000

Data Index: 128494 (C4 (Web Text))

Max Activating Token Index: 222

Text #4

Max Range: 1.4930. Min Range: -1.4930

Max Act: 1.2229. Min Act: -0.0000

Data Index: 648739 (C4 (Web Text))

Max Activating Token Index: 690

Text #5

Max Range: 1.4930. Min Range: -1.4930

Max Act: 1.3399. Min Act: -0.0000

Data Index: 972359 (C4 (Web Text))

Max Activating Token Index: 717

Text #6

Max Range: 1.4930. Min Range: -1.4930

Max Act: 1.2647. Min Act: -0.0000

Data Index: 462167 (C4 (Web Text))

Max Activating Token Index: 978

Text #7

Max Range: 1.4930. Min Range: -1.4930

Max Act: 1.2987. Min Act: -0.0000

Data Index: 1194535 (C4 (Web Text))

Max Activating Token Index: 467

Text #8

Max Range: 1.4930. Min Range: -1.4930

Max Act: 1.2146. Min Act: -0.0000

Data Index: 839127 (C4 (Web Text))

Max Activating Token Index: 403

Text #9

Max Range: 1.4930. Min Range: -1.4930

Max Act: 1.2103. Min Act: -0.0000

Data Index: 1329615 (C4 (Web Text))

Max Activating Token Index: 994

Text #10

Max Range: 1.4930. Min Range: -1.4930

Max Act: 1.1947. Min Act: -0.0000

Data Index: 1525655 (Python Code)

Max Activating Token Index: 481

Text #11

Max Range: 1.4930. Min Range: -1.4930

Max Act: 1.1920. Min Act: -0.0000

Data Index: 611835 (C4 (Web Text))

Max Activating Token Index: 473

Text #12

Max Range: 1.4930. Min Range: -1.4930

Max Act: 1.2915. Min Act: -0.0000

Data Index: 1553763 (Python Code)

Max Activating Token Index: 367

Text #13

Max Range: 1.4930. Min Range: -1.4930

Max Act: 1.2215. Min Act: -0.0000

Data Index: 1642882 (Python Code)

Max Activating Token Index: 858

Text #14

Max Range: 1.4930. Min Range: -1.4930

Max Act: 1.1915. Min Act: -0.0000

Data Index: 901016 (C4 (Web Text))

Max Activating Token Index: 294

Text #15

Max Range: 1.4930. Min Range: -1.4930

Max Act: 1.3000. Min Act: -0.0000

Data Index: 310390 (C4 (Web Text))

Max Activating Token Index: 769

Text #16

Max Range: 1.4930. Min Range: -1.4930

Max Act: 1.0666. Min Act: -0.0000

Data Index: 1334879 (C4 (Web Text))

Max Activating Token Index: 692

Text #17

Max Range: 1.4930. Min Range: -1.4930

Max Act: 1.1734. Min Act: -0.0000

Data Index: 164135 (C4 (Web Text))

Max Activating Token Index: 391

Text #18

Max Range: 1.4930. Min Range: -1.4930

Max Act: 1.1064. Min Act: -0.0000

Data Index: 30777 (C4 (Web Text))

Max Activating Token Index: 327

Text #19

Max Range: 1.4930. Min Range: -1.4930

Max Act: 1.1398. Min Act: -0.0000

Data Index: 1466247 (Python Code)

Max Activating Token Index: 439