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

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

Neuron 5251 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0711. Min Range: -2.0711

Max Act: 2.0711. Min Act: -0.0000

Data Index: 1567555 (Python Code)

Max Activating Token Index: 824

Text #1

Max Range: 2.0711. Min Range: -2.0711

Max Act: 1.7675. Min Act: -0.0000

Data Index: 167245 (C4 (Web Text))

Max Activating Token Index: 183

Text #2

Max Range: 2.0711. Min Range: -2.0711

Max Act: 1.7041. Min Act: -0.0000

Data Index: 236833 (C4 (Web Text))

Max Activating Token Index: 613

Text #3

Max Range: 2.0711. Min Range: -2.0711

Max Act: 1.6734. Min Act: -0.0000

Data Index: 472558 (C4 (Web Text))

Max Activating Token Index: 946

Text #4

Max Range: 2.0711. Min Range: -2.0711

Max Act: 1.6666. Min Act: -0.0000

Data Index: 760462 (C4 (Web Text))

Max Activating Token Index: 680

Text #5

Max Range: 2.0711. Min Range: -2.0711

Max Act: 1.7115. Min Act: -0.0000

Data Index: 308347 (C4 (Web Text))

Max Activating Token Index: 864

Text #6

Max Range: 2.0711. Min Range: -2.0711

Max Act: 1.6159. Min Act: -0.0000

Data Index: 829903 (C4 (Web Text))

Max Activating Token Index: 361

Text #7

Max Range: 2.0711. Min Range: -2.0711

Max Act: 1.5911. Min Act: -0.0000

Data Index: 117650 (C4 (Web Text))

Max Activating Token Index: 847

Text #8

Max Range: 2.0711. Min Range: -2.0711

Max Act: 1.5640. Min Act: -0.0000

Data Index: 1069973 (C4 (Web Text))

Max Activating Token Index: 473

Text #9

Max Range: 2.0711. Min Range: -2.0711

Max Act: 1.5669. Min Act: -0.0000

Data Index: 76938 (C4 (Web Text))

Max Activating Token Index: 218

Text #10

Max Range: 2.0711. Min Range: -2.0711

Max Act: 1.5550. Min Act: -0.0000

Data Index: 409731 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 2.0711. Min Range: -2.0711

Max Act: 1.5421. Min Act: -0.0000

Data Index: 584717 (C4 (Web Text))

Max Activating Token Index: 278

Text #12

Max Range: 2.0711. Min Range: -2.0711

Max Act: 1.5409. Min Act: -0.0000

Data Index: 1309103 (C4 (Web Text))

Max Activating Token Index: 970

Text #13

Max Range: 2.0711. Min Range: -2.0711

Max Act: 1.5457. Min Act: -0.0000

Data Index: 258555 (C4 (Web Text))

Max Activating Token Index: 284

Text #14

Max Range: 2.0711. Min Range: -2.0711

Max Act: 1.6148. Min Act: -0.0000

Data Index: 794568 (C4 (Web Text))

Max Activating Token Index: 753

Text #15

Max Range: 2.0711. Min Range: -2.0711

Max Act: 1.5148. Min Act: -0.0000

Data Index: 127171 (C4 (Web Text))

Max Activating Token Index: 889

Text #16

Max Range: 2.0711. Min Range: -2.0711

Max Act: 1.5156. Min Act: -0.0000

Data Index: 316819 (C4 (Web Text))

Max Activating Token Index: 470

Text #17

Max Range: 2.0711. Min Range: -2.0711

Max Act: 1.4255. Min Act: -0.0000

Data Index: 1178550 (C4 (Web Text))

Max Activating Token Index: 931

Text #18

Max Range: 2.0711. Min Range: -2.0711

Max Act: 1.5127. Min Act: -0.0000

Data Index: 702106 (C4 (Web Text))

Max Activating Token Index: 803

Text #19

Max Range: 2.0711. Min Range: -2.0711

Max Act: 1.5161. Min Act: -0.0000

Data Index: 981185 (C4 (Web Text))

Max Activating Token Index: 935