Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 343 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6039. Min Range: -0.6039

Max Act: 0.6039. Min Act: -0.0001

Data Index: 399360 (C4 (Web Text))

Max Activating Token Index: 485

Text #1

Max Range: 0.6039. Min Range: -0.6039

Max Act: 0.6006. Min Act: -0.0001

Data Index: 391493 (C4 (Web Text))

Max Activating Token Index: 998

Text #2

Max Range: 0.6039. Min Range: -0.6039

Max Act: 0.4843. Min Act: -0.0001

Data Index: 900517 (C4 (Web Text))

Max Activating Token Index: 1019

Text #3

Max Range: 0.6039. Min Range: -0.6039

Max Act: 0.4446. Min Act: -0.0001

Data Index: 1119576 (C4 (Web Text))

Max Activating Token Index: 560

Text #4

Max Range: 0.6039. Min Range: -0.6039

Max Act: 0.4520. Min Act: -0.0001

Data Index: 653026 (C4 (Web Text))

Max Activating Token Index: 893

Text #5

Max Range: 0.6039. Min Range: -0.6039

Max Act: 0.4353. Min Act: -0.0000

Data Index: 924133 (C4 (Web Text))

Max Activating Token Index: 388

Text #6

Max Range: 0.6039. Min Range: -0.6039

Max Act: 0.4820. Min Act: -0.0001

Data Index: 891482 (C4 (Web Text))

Max Activating Token Index: 500

Text #7

Max Range: 0.6039. Min Range: -0.6039

Max Act: 0.4727. Min Act: -0.0000

Data Index: 1052292 (C4 (Web Text))

Max Activating Token Index: 766

Text #8

Max Range: 0.6039. Min Range: -0.6039

Max Act: 0.4608. Min Act: -0.0001

Data Index: 238187 (C4 (Web Text))

Max Activating Token Index: 543

Text #9

Max Range: 0.6039. Min Range: -0.6039

Max Act: 0.4285. Min Act: -0.0000

Data Index: 695286 (C4 (Web Text))

Max Activating Token Index: 888

Text #10

Max Range: 0.6039. Min Range: -0.6039

Max Act: 0.4365. Min Act: -0.0001

Data Index: 193388 (C4 (Web Text))

Max Activating Token Index: 1011

Text #11

Max Range: 0.6039. Min Range: -0.6039

Max Act: 0.4191. Min Act: -0.0001

Data Index: 381200 (C4 (Web Text))

Max Activating Token Index: 339

Text #12

Max Range: 0.6039. Min Range: -0.6039

Max Act: 0.3964. Min Act: -0.0000

Data Index: 204859 (C4 (Web Text))

Max Activating Token Index: 891

Text #13

Max Range: 0.6039. Min Range: -0.6039

Max Act: 0.3929. Min Act: -0.0001

Data Index: 1308566 (C4 (Web Text))

Max Activating Token Index: 107

Text #14

Max Range: 0.6039. Min Range: -0.6039

Max Act: 0.3907. Min Act: -0.0001

Data Index: 1053963 (C4 (Web Text))

Max Activating Token Index: 328

Text #15

Max Range: 0.6039. Min Range: -0.6039

Max Act: 0.3817. Min Act: -0.0001

Data Index: 840061 (C4 (Web Text))

Max Activating Token Index: 204

Text #16

Max Range: 0.6039. Min Range: -0.6039

Max Act: 0.4060. Min Act: -0.0001

Data Index: 1353989 (C4 (Web Text))

Max Activating Token Index: 404

Text #17

Max Range: 0.6039. Min Range: -0.6039

Max Act: 0.3920. Min Act: -0.0001

Data Index: 113222 (C4 (Web Text))

Max Activating Token Index: 824

Text #18

Max Range: 0.6039. Min Range: -0.6039

Max Act: 0.3862. Min Act: -0.0001

Data Index: 983821 (C4 (Web Text))

Max Activating Token Index: 1019

Text #19

Max Range: 0.6039. Min Range: -0.6039

Max Act: 0.3511. Min Act: -0.0001

Data Index: 28994 (C4 (Web Text))

Max Activating Token Index: 674