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

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

Neuron 90 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3913. Min Range: -1.3913

Max Act: 1.3489. Min Act: -0.0001

Data Index: 804058 (C4 (Web Text))

Max Activating Token Index: 156

Text #1

Max Range: 1.3913. Min Range: -1.3913

Max Act: 1.3229. Min Act: -0.0001

Data Index: 520283 (C4 (Web Text))

Max Activating Token Index: 420

Text #2

Max Range: 1.3913. Min Range: -1.3913

Max Act: 1.3842. Min Act: -0.0001

Data Index: 163804 (C4 (Web Text))

Max Activating Token Index: 923

Text #3

Max Range: 1.3913. Min Range: -1.3913

Max Act: 1.1773. Min Act: -0.0001

Data Index: 1003238 (C4 (Web Text))

Max Activating Token Index: 761

Text #4

Max Range: 1.3913. Min Range: -1.3913

Max Act: 1.1881. Min Act: -0.0001

Data Index: 448533 (C4 (Web Text))

Max Activating Token Index: 885

Text #5

Max Range: 1.3913. Min Range: -1.3913

Max Act: 1.3913. Min Act: -0.0001

Data Index: 421367 (C4 (Web Text))

Max Activating Token Index: 180

Text #6

Max Range: 1.3913. Min Range: -1.3913

Max Act: 1.1704. Min Act: -0.0001

Data Index: 168274 (C4 (Web Text))

Max Activating Token Index: 892

Text #7

Max Range: 1.3913. Min Range: -1.3913

Max Act: 1.2348. Min Act: -0.0001

Data Index: 668218 (C4 (Web Text))

Max Activating Token Index: 970

Text #8

Max Range: 1.3913. Min Range: -1.3913

Max Act: 1.1616. Min Act: -0.0001

Data Index: 842823 (C4 (Web Text))

Max Activating Token Index: 1003

Text #9

Max Range: 1.3913. Min Range: -1.3913

Max Act: 1.1836. Min Act: -0.0001

Data Index: 242119 (C4 (Web Text))

Max Activating Token Index: 192

Text #10

Max Range: 1.3913. Min Range: -1.3913

Max Act: 1.2132. Min Act: -0.0001

Data Index: 739195 (C4 (Web Text))

Max Activating Token Index: 427

Text #11

Max Range: 1.3913. Min Range: -1.3913

Max Act: 1.1369. Min Act: -0.0001

Data Index: 824995 (C4 (Web Text))

Max Activating Token Index: 900

Text #12

Max Range: 1.3913. Min Range: -1.3913

Max Act: 1.1300. Min Act: -0.0001

Data Index: 297903 (C4 (Web Text))

Max Activating Token Index: 787

Text #13

Max Range: 1.3913. Min Range: -1.3913

Max Act: 1.1986. Min Act: -0.0001

Data Index: 298467 (C4 (Web Text))

Max Activating Token Index: 53

Text #14

Max Range: 1.3913. Min Range: -1.3913

Max Act: 1.1171. Min Act: -0.0001

Data Index: 553406 (C4 (Web Text))

Max Activating Token Index: 580

Text #15

Max Range: 1.3913. Min Range: -1.3913

Max Act: 1.1518. Min Act: -0.0001

Data Index: 267393 (C4 (Web Text))

Max Activating Token Index: 754

Text #16

Max Range: 1.3913. Min Range: -1.3913

Max Act: 1.1077. Min Act: -0.0001

Data Index: 479316 (C4 (Web Text))

Max Activating Token Index: 40

Text #17

Max Range: 1.3913. Min Range: -1.3913

Max Act: 1.1487. Min Act: -0.0001

Data Index: 537562 (C4 (Web Text))

Max Activating Token Index: 258

Text #18

Max Range: 1.3913. Min Range: -1.3913

Max Act: 1.1618. Min Act: -0.0001

Data Index: 332668 (C4 (Web Text))

Max Activating Token Index: 121

Text #19

Max Range: 1.3913. Min Range: -1.3913

Max Act: 1.1273. Min Act: -0.0001

Data Index: 1178346 (C4 (Web Text))

Max Activating Token Index: 441