Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1076 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.5661. Min Act: -0.0000

Data Index: 1169306 (C4 (Web Text))

Max Activating Token Index: 553

Text #1

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.3723. Min Act: -0.0000

Data Index: 1003091 (C4 (Web Text))

Max Activating Token Index: 963

Text #2

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.4032. Min Act: -0.0000

Data Index: 294317 (C4 (Web Text))

Max Activating Token Index: 429

Text #3

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.3716. Min Act: -0.0000

Data Index: 801775 (C4 (Web Text))

Max Activating Token Index: 522

Text #4

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.3098. Min Act: -0.0000

Data Index: 660923 (C4 (Web Text))

Max Activating Token Index: 908

Text #5

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.3510. Min Act: -0.0000

Data Index: 707512 (C4 (Web Text))

Max Activating Token Index: 75

Text #6

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.3478. Min Act: -0.0000

Data Index: 1203159 (C4 (Web Text))

Max Activating Token Index: 627

Text #7

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.3227. Min Act: -0.0000

Data Index: 659454 (C4 (Web Text))

Max Activating Token Index: 44

Text #8

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.3198. Min Act: -0.0001

Data Index: 664185 (C4 (Web Text))

Max Activating Token Index: 956

Text #9

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.3293. Min Act: -0.0000

Data Index: 761086 (C4 (Web Text))

Max Activating Token Index: 341

Text #10

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.3165. Min Act: -0.0000

Data Index: 611152 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.3012. Min Act: -0.0000

Data Index: 61774 (C4 (Web Text))

Max Activating Token Index: 218

Text #12

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.3163. Min Act: -0.0000

Data Index: 965708 (C4 (Web Text))

Max Activating Token Index: 33

Text #13

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.2945. Min Act: -0.0000

Data Index: 1307157 (C4 (Web Text))

Max Activating Token Index: 979

Text #14

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.3037. Min Act: -0.0000

Data Index: 1168554 (C4 (Web Text))

Max Activating Token Index: 526

Text #15

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.3138. Min Act: -0.0000

Data Index: 624971 (C4 (Web Text))

Max Activating Token Index: 150

Text #16

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.3148. Min Act: -0.0000

Data Index: 1217333 (C4 (Web Text))

Max Activating Token Index: 990

Text #17

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.2674. Min Act: -0.0000

Data Index: 142761 (C4 (Web Text))

Max Activating Token Index: 805

Text #18

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.3210. Min Act: -0.0000

Data Index: 381773 (C4 (Web Text))

Max Activating Token Index: 536

Text #19

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.3024. Min Act: -0.0001

Data Index: 594348 (C4 (Web Text))

Max Activating Token Index: 835