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

Dataset: The Pile

Neuron 2700 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2158. Min Range: -1.2158

Max Act: 1.2158. Min Act: -0.0000

Data Index: 945030 (The Pile)

Max Activating Token Index: 475

Text #1

Max Range: 1.2158. Min Range: -1.2158

Max Act: 1.1881. Min Act: -0.0000

Data Index: 1092946 (The Pile)

Max Activating Token Index: 760

Text #2

Max Range: 1.2158. Min Range: -1.2158

Max Act: 1.1893. Min Act: -0.0000

Data Index: 1337029 (The Pile)

Max Activating Token Index: 549

Text #3

Max Range: 1.2158. Min Range: -1.2158

Max Act: 1.1371. Min Act: -0.0000

Data Index: 1138298 (The Pile)

Max Activating Token Index: 92

Text #4

Max Range: 1.2158. Min Range: -1.2158

Max Act: 1.1034. Min Act: -0.0000

Data Index: 305071 (The Pile)

Max Activating Token Index: 273

Text #5

Max Range: 1.2158. Min Range: -1.2158

Max Act: 1.1341. Min Act: -0.0000

Data Index: 1168689 (The Pile)

Max Activating Token Index: 429

Text #6

Max Range: 1.2158. Min Range: -1.2158

Max Act: 1.1834. Min Act: -0.0000

Data Index: 982835 (The Pile)

Max Activating Token Index: 979

Text #7

Max Range: 1.2158. Min Range: -1.2158

Max Act: 1.0620. Min Act: -0.0000

Data Index: 1724110 (The Pile)

Max Activating Token Index: 82

Text #8

Max Range: 1.2158. Min Range: -1.2158

Max Act: 1.1195. Min Act: -0.0000

Data Index: 1668088 (The Pile)

Max Activating Token Index: 435

Text #9

Max Range: 1.2158. Min Range: -1.2158

Max Act: 1.0821. Min Act: -0.0000

Data Index: 1236805 (The Pile)

Max Activating Token Index: 547

Text #10

Max Range: 1.2158. Min Range: -1.2158

Max Act: 1.1094. Min Act: -0.0000

Data Index: 433732 (The Pile)

Max Activating Token Index: 93

Text #11

Max Range: 1.2158. Min Range: -1.2158

Max Act: 1.1041. Min Act: -0.0000

Data Index: 1245845 (The Pile)

Max Activating Token Index: 380

Text #12

Max Range: 1.2158. Min Range: -1.2158

Max Act: 1.0397. Min Act: -0.0000

Data Index: 961996 (The Pile)

Max Activating Token Index: 855

Text #13

Max Range: 1.2158. Min Range: -1.2158

Max Act: 1.0978. Min Act: -0.0000

Data Index: 469955 (The Pile)

Max Activating Token Index: 489

Text #14

Max Range: 1.2158. Min Range: -1.2158

Max Act: 1.0833. Min Act: -0.0000

Data Index: 1457392 (The Pile)

Max Activating Token Index: 957

Text #15

Max Range: 1.2158. Min Range: -1.2158

Max Act: 0.9815. Min Act: -0.0000

Data Index: 1517427 (The Pile)

Max Activating Token Index: 809

Text #16

Max Range: 1.2158. Min Range: -1.2158

Max Act: 1.0072. Min Act: -0.0000

Data Index: 984507 (The Pile)

Max Activating Token Index: 557

Text #17

Max Range: 1.2158. Min Range: -1.2158

Max Act: 1.0389. Min Act: -0.0000

Data Index: 1882968 (The Pile)

Max Activating Token Index: 319

Text #18

Max Range: 1.2158. Min Range: -1.2158

Max Act: 1.0659. Min Act: -0.0000

Data Index: 1129337 (The Pile)

Max Activating Token Index: 572

Text #19

Max Range: 1.2158. Min Range: -1.2158

Max Act: 1.0298. Min Act: -0.0000

Data Index: 1244602 (The Pile)

Max Activating Token Index: 285