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

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

Neuron 1404 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5328. Min Range: -4.5328

Max Act: 4.5328. Min Act: -0.0000

Data Index: 1352025 (C4 (Web Text))

Max Activating Token Index: 342

Text #1

Max Range: 4.5328. Min Range: -4.5328

Max Act: 3.7499. Min Act: -0.0000

Data Index: 606679 (C4 (Web Text))

Max Activating Token Index: 993

Text #2

Max Range: 4.5328. Min Range: -4.5328

Max Act: 3.1828. Min Act: -0.0000

Data Index: 1044504 (C4 (Web Text))

Max Activating Token Index: 3

Text #3

Max Range: 4.5328. Min Range: -4.5328

Max Act: 2.9767. Min Act: -0.0000

Data Index: 83329 (C4 (Web Text))

Max Activating Token Index: 1019

Text #4

Max Range: 4.5328. Min Range: -4.5328

Max Act: 3.1245. Min Act: -0.0000

Data Index: 1217639 (C4 (Web Text))

Max Activating Token Index: 216

Text #5

Max Range: 4.5328. Min Range: -4.5328

Max Act: 2.8950. Min Act: -0.0000

Data Index: 946741 (C4 (Web Text))

Max Activating Token Index: 208

Text #6

Max Range: 4.5328. Min Range: -4.5328

Max Act: 2.7957. Min Act: -0.0000

Data Index: 129901 (C4 (Web Text))

Max Activating Token Index: 310

Text #7

Max Range: 4.5328. Min Range: -4.5328

Max Act: 2.6119. Min Act: -0.0000

Data Index: 460605 (C4 (Web Text))

Max Activating Token Index: 404

Text #8

Max Range: 4.5328. Min Range: -4.5328

Max Act: 2.8780. Min Act: -0.0000

Data Index: 1292709 (C4 (Web Text))

Max Activating Token Index: 606

Text #9

Max Range: 4.5328. Min Range: -4.5328

Max Act: 2.5495. Min Act: -0.0000

Data Index: 582217 (C4 (Web Text))

Max Activating Token Index: 106

Text #10

Max Range: 4.5328. Min Range: -4.5328

Max Act: 2.5472. Min Act: -0.0000

Data Index: 24587 (C4 (Web Text))

Max Activating Token Index: 17

Text #11

Max Range: 4.5328. Min Range: -4.5328

Max Act: 2.5129. Min Act: -0.0000

Data Index: 624449 (C4 (Web Text))

Max Activating Token Index: 37

Text #12

Max Range: 4.5328. Min Range: -4.5328

Max Act: 2.4897. Min Act: -0.0000

Data Index: 142523 (C4 (Web Text))

Max Activating Token Index: 745

Text #13

Max Range: 4.5328. Min Range: -4.5328

Max Act: 2.4089. Min Act: -0.0000

Data Index: 489675 (C4 (Web Text))

Max Activating Token Index: 916

Text #14

Max Range: 4.5328. Min Range: -4.5328

Max Act: 2.4109. Min Act: -0.0000

Data Index: 683105 (C4 (Web Text))

Max Activating Token Index: 477

Text #15

Max Range: 4.5328. Min Range: -4.5328

Max Act: 2.3994. Min Act: -0.0000

Data Index: 840199 (C4 (Web Text))

Max Activating Token Index: 184

Text #16

Max Range: 4.5328. Min Range: -4.5328

Max Act: 2.3916. Min Act: -0.0000

Data Index: 169333 (C4 (Web Text))

Max Activating Token Index: 59

Text #17

Max Range: 4.5328. Min Range: -4.5328

Max Act: 2.3793. Min Act: -0.0000

Data Index: 115828 (C4 (Web Text))

Max Activating Token Index: 53

Text #18

Max Range: 4.5328. Min Range: -4.5328

Max Act: 2.3782. Min Act: -0.0000

Data Index: 963550 (C4 (Web Text))

Max Activating Token Index: 388

Text #19

Max Range: 4.5328. Min Range: -4.5328

Max Act: 2.3554. Min Act: -0.0000

Data Index: 145864 (C4 (Web Text))

Max Activating Token Index: 463