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

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

Neuron 1204 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2812. Min Range: -1.2812

Max Act: 1.2812. Min Act: -0.0000

Data Index: 569662 (C4 (Web Text))

Max Activating Token Index: 719

Text #1

Max Range: 1.2812. Min Range: -1.2812

Max Act: 1.0114. Min Act: -0.0000

Data Index: 642507 (C4 (Web Text))

Max Activating Token Index: 488

Text #2

Max Range: 1.2812. Min Range: -1.2812

Max Act: 1.0193. Min Act: -0.0000

Data Index: 530399 (C4 (Web Text))

Max Activating Token Index: 955

Text #3

Max Range: 1.2812. Min Range: -1.2812

Max Act: 1.0057. Min Act: -0.0000

Data Index: 559476 (C4 (Web Text))

Max Activating Token Index: 1021

Text #4

Max Range: 1.2812. Min Range: -1.2812

Max Act: 0.9343. Min Act: -0.0000

Data Index: 848961 (C4 (Web Text))

Max Activating Token Index: 521

Text #5

Max Range: 1.2812. Min Range: -1.2812

Max Act: 0.9127. Min Act: -0.0000

Data Index: 1207098 (C4 (Web Text))

Max Activating Token Index: 486

Text #6

Max Range: 1.2812. Min Range: -1.2812

Max Act: 0.9261. Min Act: 0.0000

Data Index: 1241741 (C4 (Web Text))

Max Activating Token Index: 458

Text #7

Max Range: 1.2812. Min Range: -1.2812

Max Act: 0.9151. Min Act: -0.0000

Data Index: 903619 (C4 (Web Text))

Max Activating Token Index: 898

Text #8

Max Range: 1.2812. Min Range: -1.2812

Max Act: 0.8912. Min Act: -0.0000

Data Index: 476183 (C4 (Web Text))

Max Activating Token Index: 840

Text #9

Max Range: 1.2812. Min Range: -1.2812

Max Act: 0.8911. Min Act: -0.0000

Data Index: 897947 (C4 (Web Text))

Max Activating Token Index: 763

Text #10

Max Range: 1.2812. Min Range: -1.2812

Max Act: 0.8799. Min Act: -0.0000

Data Index: 9121 (C4 (Web Text))

Max Activating Token Index: 989

Text #11

Max Range: 1.2812. Min Range: -1.2812

Max Act: 0.8651. Min Act: -0.0000

Data Index: 576879 (C4 (Web Text))

Max Activating Token Index: 782

Text #12

Max Range: 1.2812. Min Range: -1.2812

Max Act: 0.8624. Min Act: -0.0000

Data Index: 201224 (C4 (Web Text))

Max Activating Token Index: 870

Text #13

Max Range: 1.2812. Min Range: -1.2812

Max Act: 0.8631. Min Act: -0.0000

Data Index: 949569 (C4 (Web Text))

Max Activating Token Index: 419

Text #14

Max Range: 1.2812. Min Range: -1.2812

Max Act: 0.7936. Min Act: -0.0000

Data Index: 73924 (C4 (Web Text))

Max Activating Token Index: 262

Text #15

Max Range: 1.2812. Min Range: -1.2812

Max Act: 0.8471. Min Act: -0.0000

Data Index: 256334 (C4 (Web Text))

Max Activating Token Index: 539

Text #16

Max Range: 1.2812. Min Range: -1.2812

Max Act: 0.8409. Min Act: -0.0000

Data Index: 420323 (C4 (Web Text))

Max Activating Token Index: 871

Text #17

Max Range: 1.2812. Min Range: -1.2812

Max Act: 0.8282. Min Act: -0.0000

Data Index: 249912 (C4 (Web Text))

Max Activating Token Index: 917

Text #18

Max Range: 1.2812. Min Range: -1.2812

Max Act: 0.8286. Min Act: -0.0000

Data Index: 885698 (C4 (Web Text))

Max Activating Token Index: 332

Text #19

Max Range: 1.2812. Min Range: -1.2812

Max Act: 0.8199. Min Act: -0.0000

Data Index: 836454 (C4 (Web Text))

Max Activating Token Index: 279