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

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

Neuron 3458 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9462. Min Range: -0.9462

Max Act: 0.9462. Min Act: -0.0000

Data Index: 1268888 (C4 (Web Text))

Max Activating Token Index: 611

Text #1

Max Range: 0.9462. Min Range: -0.9462

Max Act: 0.8583. Min Act: -0.0000

Data Index: 676499 (C4 (Web Text))

Max Activating Token Index: 892

Text #2

Max Range: 0.9462. Min Range: -0.9462

Max Act: 0.8561. Min Act: 0.0000

Data Index: 941914 (C4 (Web Text))

Max Activating Token Index: 790

Text #3

Max Range: 0.9462. Min Range: -0.9462

Max Act: 0.7989. Min Act: -0.0000

Data Index: 268170 (C4 (Web Text))

Max Activating Token Index: 770

Text #4

Max Range: 0.9462. Min Range: -0.9462

Max Act: 0.8132. Min Act: -0.0000

Data Index: 1036665 (C4 (Web Text))

Max Activating Token Index: 154

Text #5

Max Range: 0.9462. Min Range: -0.9462

Max Act: 0.7235. Min Act: -0.0000

Data Index: 420968 (C4 (Web Text))

Max Activating Token Index: 271

Text #6

Max Range: 0.9462. Min Range: -0.9462

Max Act: 0.7657. Min Act: -0.0000

Data Index: 913224 (C4 (Web Text))

Max Activating Token Index: 267

Text #7

Max Range: 0.9462. Min Range: -0.9462

Max Act: 0.7579. Min Act: -0.0000

Data Index: 1230498 (C4 (Web Text))

Max Activating Token Index: 331

Text #8

Max Range: 0.9462. Min Range: -0.9462

Max Act: 0.7159. Min Act: -0.0000

Data Index: 507857 (C4 (Web Text))

Max Activating Token Index: 618

Text #9

Max Range: 0.9462. Min Range: -0.9462

Max Act: 0.7677. Min Act: -0.0000

Data Index: 45597 (C4 (Web Text))

Max Activating Token Index: 888

Text #10

Max Range: 0.9462. Min Range: -0.9462

Max Act: 0.6719. Min Act: -0.0000

Data Index: 457020 (C4 (Web Text))

Max Activating Token Index: 532

Text #11

Max Range: 0.9462. Min Range: -0.9462

Max Act: 0.6844. Min Act: -0.0000

Data Index: 945534 (C4 (Web Text))

Max Activating Token Index: 258

Text #12

Max Range: 0.9462. Min Range: -0.9462

Max Act: 0.7124. Min Act: 0.0000

Data Index: 34121 (C4 (Web Text))

Max Activating Token Index: 306

Text #13

Max Range: 0.9462. Min Range: -0.9462

Max Act: 0.7061. Min Act: -0.0000

Data Index: 105041 (C4 (Web Text))

Max Activating Token Index: 191

Text #14

Max Range: 0.9462. Min Range: -0.9462

Max Act: 0.7054. Min Act: -0.0000

Data Index: 136437 (C4 (Web Text))

Max Activating Token Index: 885

Text #15

Max Range: 0.9462. Min Range: -0.9462

Max Act: 0.6598. Min Act: -0.0000

Data Index: 113938 (C4 (Web Text))

Max Activating Token Index: 906

Text #16

Max Range: 0.9462. Min Range: -0.9462

Max Act: 0.6656. Min Act: -0.0000

Data Index: 438247 (C4 (Web Text))

Max Activating Token Index: 944

Text #17

Max Range: 0.9462. Min Range: -0.9462

Max Act: 0.6605. Min Act: -0.0000

Data Index: 769367 (C4 (Web Text))

Max Activating Token Index: 740

Text #18

Max Range: 0.9462. Min Range: -0.9462

Max Act: 0.6575. Min Act: -0.0000

Data Index: 1234038 (C4 (Web Text))

Max Activating Token Index: 634

Text #19

Max Range: 0.9462. Min Range: -0.9462

Max Act: 0.6466. Min Act: -0.0000

Data Index: 166029 (C4 (Web Text))

Max Activating Token Index: 1000