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

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

Neuron 532 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3936. Min Range: -1.3936

Max Act: 1.3181. Min Act: -0.0001

Data Index: 533547 (C4 (Web Text))

Max Activating Token Index: 6

Text #1

Max Range: 1.3936. Min Range: -1.3936

Max Act: 1.3435. Min Act: -0.0001

Data Index: 513694 (C4 (Web Text))

Max Activating Token Index: 521

Text #2

Max Range: 1.3936. Min Range: -1.3936

Max Act: 1.2927. Min Act: -0.0001

Data Index: 586017 (C4 (Web Text))

Max Activating Token Index: 99

Text #3

Max Range: 1.3936. Min Range: -1.3936

Max Act: 1.3936. Min Act: -0.0000

Data Index: 788737 (C4 (Web Text))

Max Activating Token Index: 176

Text #4

Max Range: 1.3936. Min Range: -1.3936

Max Act: 1.2498. Min Act: -0.0001

Data Index: 303606 (C4 (Web Text))

Max Activating Token Index: 472

Text #5

Max Range: 1.3936. Min Range: -1.3936

Max Act: 1.3130. Min Act: -0.0001

Data Index: 247556 (C4 (Web Text))

Max Activating Token Index: 102

Text #6

Max Range: 1.3936. Min Range: -1.3936

Max Act: 1.2253. Min Act: -0.0000

Data Index: 685999 (C4 (Web Text))

Max Activating Token Index: 92

Text #7

Max Range: 1.3936. Min Range: -1.3936

Max Act: 1.1921. Min Act: -0.0001

Data Index: 526550 (C4 (Web Text))

Max Activating Token Index: 301

Text #8

Max Range: 1.3936. Min Range: -1.3936

Max Act: 1.2740. Min Act: -0.0001

Data Index: 611097 (C4 (Web Text))

Max Activating Token Index: 282

Text #9

Max Range: 1.3936. Min Range: -1.3936

Max Act: 1.2306. Min Act: -0.0001

Data Index: 186197 (C4 (Web Text))

Max Activating Token Index: 642

Text #10

Max Range: 1.3936. Min Range: -1.3936

Max Act: 1.1023. Min Act: -0.0001

Data Index: 627723 (C4 (Web Text))

Max Activating Token Index: 135

Text #11

Max Range: 1.3936. Min Range: -1.3936

Max Act: 1.1931. Min Act: -0.0001

Data Index: 1042830 (C4 (Web Text))

Max Activating Token Index: 571

Text #12

Max Range: 1.3936. Min Range: -1.3936

Max Act: 1.1549. Min Act: -0.0001

Data Index: 32233 (C4 (Web Text))

Max Activating Token Index: 241

Text #13

Max Range: 1.3936. Min Range: -1.3936

Max Act: 1.0903. Min Act: -0.0001

Data Index: 293257 (C4 (Web Text))

Max Activating Token Index: 594

Text #14

Max Range: 1.3936. Min Range: -1.3936

Max Act: 1.1074. Min Act: -0.0001

Data Index: 426702 (C4 (Web Text))

Max Activating Token Index: 95

Text #15

Max Range: 1.3936. Min Range: -1.3936

Max Act: 1.1392. Min Act: -0.0001

Data Index: 357103 (C4 (Web Text))

Max Activating Token Index: 1003

Text #16

Max Range: 1.3936. Min Range: -1.3936

Max Act: 1.1327. Min Act: -0.0000

Data Index: 707927 (C4 (Web Text))

Max Activating Token Index: 183

Text #17

Max Range: 1.3936. Min Range: -1.3936

Max Act: 1.1711. Min Act: -0.0001

Data Index: 153986 (C4 (Web Text))

Max Activating Token Index: 346

Text #18

Max Range: 1.3936. Min Range: -1.3936

Max Act: 1.1780. Min Act: -0.0001

Data Index: 258782 (C4 (Web Text))

Max Activating Token Index: 346

Text #19

Max Range: 1.3936. Min Range: -1.3936

Max Act: 1.1154. Min Act: -0.0001

Data Index: 813498 (C4 (Web Text))

Max Activating Token Index: 10