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

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

Neuron 5727 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: 0.8044. Min Range: -0.8044

Max Act: 0.8044. Min Act: -0.0000

Data Index: 137652 (C4 (Web Text))

Max Activating Token Index: 560

Text #1

Max Range: 0.8044. Min Range: -0.8044

Max Act: 0.6917. Min Act: -0.0000

Data Index: 715928 (C4 (Web Text))

Max Activating Token Index: 596

Text #2

Max Range: 0.8044. Min Range: -0.8044

Max Act: 0.5631. Min Act: -0.0000

Data Index: 596319 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 0.8044. Min Range: -0.8044

Max Act: 0.5356. Min Act: -0.0000

Data Index: 274104 (C4 (Web Text))

Max Activating Token Index: 950

Text #4

Max Range: 0.8044. Min Range: -0.8044

Max Act: 0.4879. Min Act: -0.0000

Data Index: 716463 (C4 (Web Text))

Max Activating Token Index: 259

Text #5

Max Range: 0.8044. Min Range: -0.8044

Max Act: 0.5007. Min Act: -0.0000

Data Index: 614105 (C4 (Web Text))

Max Activating Token Index: 780

Text #6

Max Range: 0.8044. Min Range: -0.8044

Max Act: 0.5174. Min Act: -0.0000

Data Index: 405900 (C4 (Web Text))

Max Activating Token Index: 271

Text #7

Max Range: 0.8044. Min Range: -0.8044

Max Act: 0.4964. Min Act: -0.0000

Data Index: 329450 (C4 (Web Text))

Max Activating Token Index: 172

Text #8

Max Range: 0.8044. Min Range: -0.8044

Max Act: 0.4545. Min Act: -0.0000

Data Index: 595710 (C4 (Web Text))

Max Activating Token Index: 801

Text #9

Max Range: 0.8044. Min Range: -0.8044

Max Act: 0.4275. Min Act: -0.0000

Data Index: 514574 (C4 (Web Text))

Max Activating Token Index: 909

Text #10

Max Range: 0.8044. Min Range: -0.8044

Max Act: 0.4403. Min Act: -0.0000

Data Index: 84921 (C4 (Web Text))

Max Activating Token Index: 682

Text #11

Max Range: 0.8044. Min Range: -0.8044

Max Act: 0.4753. Min Act: -0.0000

Data Index: 1169042 (C4 (Web Text))

Max Activating Token Index: 656

Text #12

Max Range: 0.8044. Min Range: -0.8044

Max Act: 0.4371. Min Act: -0.0000

Data Index: 828831 (C4 (Web Text))

Max Activating Token Index: 215

Text #13

Max Range: 0.8044. Min Range: -0.8044

Max Act: 0.4386. Min Act: -0.0000

Data Index: 1346699 (C4 (Web Text))

Max Activating Token Index: 144

Text #14

Max Range: 0.8044. Min Range: -0.8044

Max Act: 0.4146. Min Act: -0.0000

Data Index: 435618 (C4 (Web Text))

Max Activating Token Index: 469

Text #15

Max Range: 0.8044. Min Range: -0.8044

Max Act: 0.4310. Min Act: -0.0000

Data Index: 1257764 (C4 (Web Text))

Max Activating Token Index: 181

Text #16

Max Range: 0.8044. Min Range: -0.8044

Max Act: 0.4555. Min Act: -0.0000

Data Index: 711830 (C4 (Web Text))

Max Activating Token Index: 494

Text #17

Max Range: 0.8044. Min Range: -0.8044

Max Act: 0.4535. Min Act: -0.0000

Data Index: 928808 (C4 (Web Text))

Max Activating Token Index: 702

Text #18

Max Range: 0.8044. Min Range: -0.8044

Max Act: 0.4469. Min Act: -0.0000

Data Index: 340761 (C4 (Web Text))

Max Activating Token Index: 711

Text #19

Max Range: 0.8044. Min Range: -0.8044

Max Act: 0.4765. Min Act: -0.0000

Data Index: 1190395 (C4 (Web Text))

Max Activating Token Index: 281