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

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

Neuron 320 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.4736. Min Act: 0.0000

Data Index: 985810 (C4 (Web Text))

Max Activating Token Index: 529

Text #1

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.4441. Min Act: -0.0000

Data Index: 660132 (C4 (Web Text))

Max Activating Token Index: 601

Text #2

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.4202. Min Act: -0.0000

Data Index: 1297851 (C4 (Web Text))

Max Activating Token Index: 533

Text #3

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.4180. Min Act: -0.0000

Data Index: 880458 (C4 (Web Text))

Max Activating Token Index: 129

Text #4

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.4046. Min Act: -0.0000

Data Index: 721140 (C4 (Web Text))

Max Activating Token Index: 571

Text #5

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.3877. Min Act: -0.0000

Data Index: 1189540 (C4 (Web Text))

Max Activating Token Index: 572

Text #6

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.4044. Min Act: -0.0000

Data Index: 1229915 (C4 (Web Text))

Max Activating Token Index: 987

Text #7

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.3716. Min Act: -0.0000

Data Index: 199309 (C4 (Web Text))

Max Activating Token Index: 591

Text #8

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.3650. Min Act: -0.0000

Data Index: 593007 (C4 (Web Text))

Max Activating Token Index: 640

Text #9

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.3517. Min Act: -0.0000

Data Index: 866602 (C4 (Web Text))

Max Activating Token Index: 809

Text #10

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.3536. Min Act: -0.0000

Data Index: 1221927 (C4 (Web Text))

Max Activating Token Index: 147

Text #11

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.3476. Min Act: -0.0000

Data Index: 1102065 (C4 (Web Text))

Max Activating Token Index: 205

Text #12

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.3674. Min Act: -0.0000

Data Index: 245080 (C4 (Web Text))

Max Activating Token Index: 178

Text #13

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.3394. Min Act: -0.0000

Data Index: 1092768 (C4 (Web Text))

Max Activating Token Index: 352

Text #14

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.3413. Min Act: -0.0000

Data Index: 1161790 (C4 (Web Text))

Max Activating Token Index: 487

Text #15

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.3280. Min Act: -0.0000

Data Index: 292204 (C4 (Web Text))

Max Activating Token Index: 947

Text #16

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.3391. Min Act: -0.0000

Data Index: 671002 (C4 (Web Text))

Max Activating Token Index: 720

Text #17

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.3108. Min Act: -0.0000

Data Index: 75267 (C4 (Web Text))

Max Activating Token Index: 920

Text #18

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.3149. Min Act: -0.0000

Data Index: 1268609 (C4 (Web Text))

Max Activating Token Index: 177

Text #19

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.3316. Min Act: -0.0000

Data Index: 945202 (C4 (Web Text))

Max Activating Token Index: 620