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

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

Neuron 2207 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8548. Min Range: -4.8548

Max Act: 4.8177. Min Act: -0.0000

Data Index: 372229 (C4 (Web Text))

Max Activating Token Index: 590

Text #1

Max Range: 4.8548. Min Range: -4.8548

Max Act: 4.7002. Min Act: -0.0000

Data Index: 1058672 (C4 (Web Text))

Max Activating Token Index: 500

Text #2

Max Range: 4.8548. Min Range: -4.8548

Max Act: 4.1514. Min Act: -0.0000

Data Index: 698265 (C4 (Web Text))

Max Activating Token Index: 402

Text #3

Max Range: 4.8548. Min Range: -4.8548

Max Act: 4.1940. Min Act: -0.0000

Data Index: 40521 (C4 (Web Text))

Max Activating Token Index: 979

Text #4

Max Range: 4.8548. Min Range: -4.8548

Max Act: 4.3298. Min Act: -0.0000

Data Index: 1148966 (C4 (Web Text))

Max Activating Token Index: 337

Text #5

Max Range: 4.8548. Min Range: -4.8548

Max Act: 4.8548. Min Act: -0.0000

Data Index: 49294 (C4 (Web Text))

Max Activating Token Index: 642

Text #6

Max Range: 4.8548. Min Range: -4.8548

Max Act: 4.2864. Min Act: -0.0000

Data Index: 1181562 (C4 (Web Text))

Max Activating Token Index: 620

Text #7

Max Range: 4.8548. Min Range: -4.8548

Max Act: 4.2565. Min Act: -0.0000

Data Index: 458466 (C4 (Web Text))

Max Activating Token Index: 623

Text #8

Max Range: 4.8548. Min Range: -4.8548

Max Act: 3.6722. Min Act: -0.0000

Data Index: 596540 (C4 (Web Text))

Max Activating Token Index: 130

Text #9

Max Range: 4.8548. Min Range: -4.8548

Max Act: 4.2693. Min Act: -0.0000

Data Index: 71060 (C4 (Web Text))

Max Activating Token Index: 220

Text #10

Max Range: 4.8548. Min Range: -4.8548

Max Act: 3.8564. Min Act: -0.0000

Data Index: 1214090 (C4 (Web Text))

Max Activating Token Index: 999

Text #11

Max Range: 4.8548. Min Range: -4.8548

Max Act: 4.4875. Min Act: -0.0000

Data Index: 1110314 (C4 (Web Text))

Max Activating Token Index: 407

Text #12

Max Range: 4.8548. Min Range: -4.8548

Max Act: 3.7802. Min Act: -0.0000

Data Index: 99465 (C4 (Web Text))

Max Activating Token Index: 193

Text #13

Max Range: 4.8548. Min Range: -4.8548

Max Act: 3.6413. Min Act: -0.0000

Data Index: 954356 (C4 (Web Text))

Max Activating Token Index: 1019

Text #14

Max Range: 4.8548. Min Range: -4.8548

Max Act: 2.5850. Min Act: -0.0000

Data Index: 278811 (C4 (Web Text))

Max Activating Token Index: 487

Text #15

Max Range: 4.8548. Min Range: -4.8548

Max Act: 2.0064. Min Act: -0.0000

Data Index: 1270448 (C4 (Web Text))

Max Activating Token Index: 805

Text #16

Max Range: 4.8548. Min Range: -4.8548

Max Act: 2.4299. Min Act: -0.0000

Data Index: 78007 (C4 (Web Text))

Max Activating Token Index: 769

Text #17

Max Range: 4.8548. Min Range: -4.8548

Max Act: 2.1658. Min Act: -0.0000

Data Index: 77237 (C4 (Web Text))

Max Activating Token Index: 618

Text #18

Max Range: 4.8548. Min Range: -4.8548

Max Act: 1.7170. Min Act: -0.0000

Data Index: 509610 (C4 (Web Text))

Max Activating Token Index: 385

Text #19

Max Range: 4.8548. Min Range: -4.8548

Max Act: 1.1067. Min Act: -0.0000

Data Index: 1035329 (C4 (Web Text))

Max Activating Token Index: 63