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

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

Neuron 1352 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9038. Min Range: -2.9038

Max Act: 2.9038. Min Act: -0.0000

Data Index: 469538 (C4 (Web Text))

Max Activating Token Index: 235

Text #1

Max Range: 2.9038. Min Range: -2.9038

Max Act: 2.5874. Min Act: -0.0000

Data Index: 1127495 (C4 (Web Text))

Max Activating Token Index: 406

Text #2

Max Range: 2.9038. Min Range: -2.9038

Max Act: 2.3186. Min Act: -0.0000

Data Index: 826865 (C4 (Web Text))

Max Activating Token Index: 887

Text #3

Max Range: 2.9038. Min Range: -2.9038

Max Act: 2.2749. Min Act: -0.0000

Data Index: 1250692 (C4 (Web Text))

Max Activating Token Index: 318

Text #4

Max Range: 2.9038. Min Range: -2.9038

Max Act: 2.2665. Min Act: -0.0000

Data Index: 951044 (C4 (Web Text))

Max Activating Token Index: 145

Text #5

Max Range: 2.9038. Min Range: -2.9038

Max Act: 2.1566. Min Act: -0.0000

Data Index: 168704 (C4 (Web Text))

Max Activating Token Index: 443

Text #6

Max Range: 2.9038. Min Range: -2.9038

Max Act: 2.0319. Min Act: -0.0000

Data Index: 172887 (C4 (Web Text))

Max Activating Token Index: 1018

Text #7

Max Range: 2.9038. Min Range: -2.9038

Max Act: 2.0463. Min Act: -0.0000

Data Index: 680561 (C4 (Web Text))

Max Activating Token Index: 983

Text #8

Max Range: 2.9038. Min Range: -2.9038

Max Act: 2.0945. Min Act: -0.0000

Data Index: 203893 (C4 (Web Text))

Max Activating Token Index: 745

Text #9

Max Range: 2.9038. Min Range: -2.9038

Max Act: 2.0402. Min Act: -0.0000

Data Index: 479573 (C4 (Web Text))

Max Activating Token Index: 237

Text #10

Max Range: 2.9038. Min Range: -2.9038

Max Act: 2.2495. Min Act: -0.0000

Data Index: 529196 (C4 (Web Text))

Max Activating Token Index: 832

Text #11

Max Range: 2.9038. Min Range: -2.9038

Max Act: 1.9734. Min Act: -0.0000

Data Index: 754417 (C4 (Web Text))

Max Activating Token Index: 602

Text #12

Max Range: 2.9038. Min Range: -2.9038

Max Act: 1.9676. Min Act: -0.0000

Data Index: 45545 (C4 (Web Text))

Max Activating Token Index: 528

Text #13

Max Range: 2.9038. Min Range: -2.9038

Max Act: 1.9591. Min Act: -0.0000

Data Index: 857352 (C4 (Web Text))

Max Activating Token Index: 990

Text #14

Max Range: 2.9038. Min Range: -2.9038

Max Act: 1.9194. Min Act: -0.0000

Data Index: 30164 (C4 (Web Text))

Max Activating Token Index: 169

Text #15

Max Range: 2.9038. Min Range: -2.9038

Max Act: 1.9181. Min Act: -0.0000

Data Index: 173980 (C4 (Web Text))

Max Activating Token Index: 458

Text #16

Max Range: 2.9038. Min Range: -2.9038

Max Act: 1.9160. Min Act: -0.0000

Data Index: 73241 (C4 (Web Text))

Max Activating Token Index: 146

Text #17

Max Range: 2.9038. Min Range: -2.9038

Max Act: 1.8209. Min Act: -0.0000

Data Index: 865082 (C4 (Web Text))

Max Activating Token Index: 638

Text #18

Max Range: 2.9038. Min Range: -2.9038

Max Act: 1.9144. Min Act: -0.0000

Data Index: 923030 (C4 (Web Text))

Max Activating Token Index: 951

Text #19

Max Range: 2.9038. Min Range: -2.9038

Max Act: 1.9200. Min Act: -0.0000

Data Index: 1363047 (Python Code)

Max Activating Token Index: 246