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

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

Neuron 928 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4606. Min Range: -0.4606

Max Act: 0.4606. Min Act: -0.0001

Data Index: 497865 (C4 (Web Text))

Max Activating Token Index: 687

Text #1

Max Range: 0.4606. Min Range: -0.4606

Max Act: 0.4239. Min Act: -0.0000

Data Index: 668155 (C4 (Web Text))

Max Activating Token Index: 605

Text #2

Max Range: 0.4606. Min Range: -0.4606

Max Act: 0.3914. Min Act: -0.0000

Data Index: 399791 (C4 (Web Text))

Max Activating Token Index: 586

Text #3

Max Range: 0.4606. Min Range: -0.4606

Max Act: 0.3699. Min Act: -0.0000

Data Index: 682435 (C4 (Web Text))

Max Activating Token Index: 734

Text #4

Max Range: 0.4606. Min Range: -0.4606

Max Act: 0.3490. Min Act: -0.0000

Data Index: 1235011 (C4 (Web Text))

Max Activating Token Index: 345

Text #5

Max Range: 0.4606. Min Range: -0.4606

Max Act: 0.3330. Min Act: -0.0001

Data Index: 1151680 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 0.4606. Min Range: -0.4606

Max Act: 0.3526. Min Act: -0.0001

Data Index: 840455 (C4 (Web Text))

Max Activating Token Index: 886

Text #7

Max Range: 0.4606. Min Range: -0.4606

Max Act: 0.3366. Min Act: -0.0001

Data Index: 1200664 (C4 (Web Text))

Max Activating Token Index: 503

Text #8

Max Range: 0.4606. Min Range: -0.4606

Max Act: 0.3385. Min Act: -0.0000

Data Index: 138311 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 0.4606. Min Range: -0.4606

Max Act: 0.3335. Min Act: -0.0001

Data Index: 445972 (C4 (Web Text))

Max Activating Token Index: 197

Text #10

Max Range: 0.4606. Min Range: -0.4606

Max Act: 0.3215. Min Act: -0.0000

Data Index: 881672 (C4 (Web Text))

Max Activating Token Index: 436

Text #11

Max Range: 0.4606. Min Range: -0.4606

Max Act: 0.3403. Min Act: -0.0000

Data Index: 516298 (C4 (Web Text))

Max Activating Token Index: 741

Text #12

Max Range: 0.4606. Min Range: -0.4606

Max Act: 0.3248. Min Act: -0.0001

Data Index: 604492 (C4 (Web Text))

Max Activating Token Index: 648

Text #13

Max Range: 0.4606. Min Range: -0.4606

Max Act: 0.3204. Min Act: -0.0000

Data Index: 1162023 (C4 (Web Text))

Max Activating Token Index: 1011

Text #14

Max Range: 0.4606. Min Range: -0.4606

Max Act: 0.2962. Min Act: -0.0000

Data Index: 122917 (C4 (Web Text))

Max Activating Token Index: 269

Text #15

Max Range: 0.4606. Min Range: -0.4606

Max Act: 0.3013. Min Act: -0.0001

Data Index: 816873 (C4 (Web Text))

Max Activating Token Index: 334

Text #16

Max Range: 0.4606. Min Range: -0.4606

Max Act: 0.3088. Min Act: -0.0000

Data Index: 307385 (C4 (Web Text))

Max Activating Token Index: 234

Text #17

Max Range: 0.4606. Min Range: -0.4606

Max Act: 0.2971. Min Act: -0.0001

Data Index: 516170 (C4 (Web Text))

Max Activating Token Index: 515

Text #18

Max Range: 0.4606. Min Range: -0.4606

Max Act: 0.3077. Min Act: -0.0001

Data Index: 469728 (C4 (Web Text))

Max Activating Token Index: 919

Text #19

Max Range: 0.4606. Min Range: -0.4606

Max Act: 0.3074. Min Act: -0.0001

Data Index: 1110978 (C4 (Web Text))

Max Activating Token Index: 816