Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1053 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.4495. Min Act: -0.0002

Data Index: 733992 (C4 (Web Text))

Max Activating Token Index: 996

Text #1

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.4382. Min Act: -0.0002

Data Index: 771264 (C4 (Web Text))

Max Activating Token Index: 938

Text #2

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.4698. Min Act: -0.0002

Data Index: 618015 (C4 (Web Text))

Max Activating Token Index: 687

Text #3

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.4073. Min Act: -0.0002

Data Index: 15436 (C4 (Web Text))

Max Activating Token Index: 365

Text #4

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.4011. Min Act: -0.0002

Data Index: 138657 (C4 (Web Text))

Max Activating Token Index: 614

Text #5

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3611. Min Act: -0.0002

Data Index: 556269 (C4 (Web Text))

Max Activating Token Index: 337

Text #6

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3590. Min Act: -0.0002

Data Index: 971677 (C4 (Web Text))

Max Activating Token Index: 504

Text #7

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3644. Min Act: -0.0002

Data Index: 710437 (C4 (Web Text))

Max Activating Token Index: 164

Text #8

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3814. Min Act: -0.0002

Data Index: 686693 (C4 (Web Text))

Max Activating Token Index: 40

Text #9

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3341. Min Act: -0.0002

Data Index: 862324 (C4 (Web Text))

Max Activating Token Index: 995

Text #10

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3556. Min Act: -0.0001

Data Index: 811668 (C4 (Web Text))

Max Activating Token Index: 16

Text #11

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3305. Min Act: -0.0001

Data Index: 925408 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3054. Min Act: -0.0002

Data Index: 1177089 (C4 (Web Text))

Max Activating Token Index: 70

Text #13

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3284. Min Act: -0.0002

Data Index: 796167 (C4 (Web Text))

Max Activating Token Index: 756

Text #14

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3167. Min Act: -0.0002

Data Index: 353714 (C4 (Web Text))

Max Activating Token Index: 410

Text #15

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.2942. Min Act: -0.0000

Data Index: 10429 (C4 (Web Text))

Max Activating Token Index: 403

Text #16

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3116. Min Act: -0.0002

Data Index: 306898 (C4 (Web Text))

Max Activating Token Index: 165

Text #17

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.2941. Min Act: -0.0002

Data Index: 1015894 (C4 (Web Text))

Max Activating Token Index: 80

Text #18

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3099. Min Act: -0.0002

Data Index: 197594 (C4 (Web Text))

Max Activating Token Index: 727

Text #19

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.2956. Min Act: -0.0002

Data Index: 429066 (C4 (Web Text))

Max Activating Token Index: 41