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

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

Neuron 4102 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9403. Min Range: -2.9403

Max Act: 2.7956. Min Act: -0.0000

Data Index: 343631 (C4 (Web Text))

Max Activating Token Index: 887

Text #1

Max Range: 2.9403. Min Range: -2.9403

Max Act: 2.9403. Min Act: -0.0000

Data Index: 1173011 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 2.9403. Min Range: -2.9403

Max Act: 2.5942. Min Act: -0.0000

Data Index: 819550 (C4 (Web Text))

Max Activating Token Index: 489

Text #3

Max Range: 2.9403. Min Range: -2.9403

Max Act: 2.5834. Min Act: -0.0000

Data Index: 16876 (C4 (Web Text))

Max Activating Token Index: 560

Text #4

Max Range: 2.9403. Min Range: -2.9403

Max Act: 2.5355. Min Act: -0.0000

Data Index: 643386 (C4 (Web Text))

Max Activating Token Index: 134

Text #5

Max Range: 2.9403. Min Range: -2.9403

Max Act: 2.2412. Min Act: -0.0000

Data Index: 1119040 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 2.9403. Min Range: -2.9403

Max Act: 2.3094. Min Act: -0.0000

Data Index: 656501 (C4 (Web Text))

Max Activating Token Index: 611

Text #7

Max Range: 2.9403. Min Range: -2.9403

Max Act: 2.3090. Min Act: -0.0000

Data Index: 345173 (C4 (Web Text))

Max Activating Token Index: 454

Text #8

Max Range: 2.9403. Min Range: -2.9403

Max Act: 2.1749. Min Act: -0.0000

Data Index: 652050 (C4 (Web Text))

Max Activating Token Index: 452

Text #9

Max Range: 2.9403. Min Range: -2.9403

Max Act: 1.8660. Min Act: -0.0000

Data Index: 147069 (C4 (Web Text))

Max Activating Token Index: 878

Text #10

Max Range: 2.9403. Min Range: -2.9403

Max Act: 1.9506. Min Act: -0.0000

Data Index: 1206891 (C4 (Web Text))

Max Activating Token Index: 367

Text #11

Max Range: 2.9403. Min Range: -2.9403

Max Act: 1.7436. Min Act: -0.0000

Data Index: 1279112 (C4 (Web Text))

Max Activating Token Index: 585

Text #12

Max Range: 2.9403. Min Range: -2.9403

Max Act: 1.7978. Min Act: -0.0000

Data Index: 27156 (C4 (Web Text))

Max Activating Token Index: 285

Text #13

Max Range: 2.9403. Min Range: -2.9403

Max Act: 1.7267. Min Act: -0.0000

Data Index: 828167 (C4 (Web Text))

Max Activating Token Index: 131

Text #14

Max Range: 2.9403. Min Range: -2.9403

Max Act: 1.5846. Min Act: 0.0000

Data Index: 456905 (C4 (Web Text))

Max Activating Token Index: 651

Text #15

Max Range: 2.9403. Min Range: -2.9403

Max Act: 1.9305. Min Act: 0.0000

Data Index: 1309632 (C4 (Web Text))

Max Activating Token Index: 838

Text #16

Max Range: 2.9403. Min Range: -2.9403

Max Act: 1.6103. Min Act: -0.0000

Data Index: 1132159 (C4 (Web Text))

Max Activating Token Index: 565

Text #17

Max Range: 2.9403. Min Range: -2.9403

Max Act: 1.6202. Min Act: -0.0000

Data Index: 821427 (C4 (Web Text))

Max Activating Token Index: 97

Text #18

Max Range: 2.9403. Min Range: -2.9403

Max Act: 1.6517. Min Act: -0.0000

Data Index: 664063 (C4 (Web Text))

Max Activating Token Index: 352

Text #19

Max Range: 2.9403. Min Range: -2.9403

Max Act: 1.4983. Min Act: -0.0000

Data Index: 1092941 (C4 (Web Text))

Max Activating Token Index: 150