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

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

Neuron 306 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0472. Min Range: -4.0472

Max Act: 3.9126. Min Act: -0.0001

Data Index: 611054 (C4 (Web Text))

Max Activating Token Index: 152

Text #1

Max Range: 4.0472. Min Range: -4.0472

Max Act: 4.0472. Min Act: -0.0001

Data Index: 707152 (C4 (Web Text))

Max Activating Token Index: 251

Text #2

Max Range: 4.0472. Min Range: -4.0472

Max Act: 3.9105. Min Act: -0.0001

Data Index: 194182 (C4 (Web Text))

Max Activating Token Index: 39

Text #3

Max Range: 4.0472. Min Range: -4.0472

Max Act: 4.0133. Min Act: -0.0001

Data Index: 875926 (C4 (Web Text))

Max Activating Token Index: 407

Text #4

Max Range: 4.0472. Min Range: -4.0472

Max Act: 3.8451. Min Act: -0.0001

Data Index: 14271 (C4 (Web Text))

Max Activating Token Index: 100

Text #5

Max Range: 4.0472. Min Range: -4.0472

Max Act: 3.6304. Min Act: -0.0001

Data Index: 469168 (C4 (Web Text))

Max Activating Token Index: 419

Text #6

Max Range: 4.0472. Min Range: -4.0472

Max Act: 3.7501. Min Act: -0.0001

Data Index: 141518 (C4 (Web Text))

Max Activating Token Index: 181

Text #7

Max Range: 4.0472. Min Range: -4.0472

Max Act: 3.5859. Min Act: -0.0001

Data Index: 21622 (C4 (Web Text))

Max Activating Token Index: 246

Text #8

Max Range: 4.0472. Min Range: -4.0472

Max Act: 3.4966. Min Act: -0.0001

Data Index: 1254377 (C4 (Web Text))

Max Activating Token Index: 400

Text #9

Max Range: 4.0472. Min Range: -4.0472

Max Act: 3.5828. Min Act: -0.0001

Data Index: 1003948 (C4 (Web Text))

Max Activating Token Index: 608

Text #10

Max Range: 4.0472. Min Range: -4.0472

Max Act: 3.3684. Min Act: -0.0001

Data Index: 109096 (C4 (Web Text))

Max Activating Token Index: 109

Text #11

Max Range: 4.0472. Min Range: -4.0472

Max Act: 3.3345. Min Act: -0.0001

Data Index: 20053 (C4 (Web Text))

Max Activating Token Index: 328

Text #12

Max Range: 4.0472. Min Range: -4.0472

Max Act: 3.3082. Min Act: -0.0001

Data Index: 1021365 (C4 (Web Text))

Max Activating Token Index: 532

Text #13

Max Range: 4.0472. Min Range: -4.0472

Max Act: 3.2722. Min Act: -0.0001

Data Index: 1291223 (C4 (Web Text))

Max Activating Token Index: 666

Text #14

Max Range: 4.0472. Min Range: -4.0472

Max Act: 3.1547. Min Act: -0.0001

Data Index: 1217906 (C4 (Web Text))

Max Activating Token Index: 790

Text #15

Max Range: 4.0472. Min Range: -4.0472

Max Act: 3.0211. Min Act: -0.0001

Data Index: 835136 (C4 (Web Text))

Max Activating Token Index: 890

Text #16

Max Range: 4.0472. Min Range: -4.0472

Max Act: 2.8644. Min Act: -0.0001

Data Index: 1236410 (C4 (Web Text))

Max Activating Token Index: 835

Text #17

Max Range: 4.0472. Min Range: -4.0472

Max Act: 3.0898. Min Act: -0.0001

Data Index: 837014 (C4 (Web Text))

Max Activating Token Index: 918

Text #18

Max Range: 4.0472. Min Range: -4.0472

Max Act: 3.2378. Min Act: -0.0001

Data Index: 325451 (C4 (Web Text))

Max Activating Token Index: 778

Text #19

Max Range: 4.0472. Min Range: -4.0472

Max Act: 2.9630. Min Act: -0.0001

Data Index: 436008 (C4 (Web Text))

Max Activating Token Index: 158