Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2109 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.2361. Min Act: -0.0003

Data Index: 984464 (C4 (Web Text))

Max Activating Token Index: 670

Text #1

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.2207. Min Act: -0.0003

Data Index: 1034028 (C4 (Web Text))

Max Activating Token Index: 858

Text #2

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.2044. Min Act: -0.0003

Data Index: 395857 (C4 (Web Text))

Max Activating Token Index: 525

Text #3

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.2045. Min Act: -0.0003

Data Index: 1190313 (C4 (Web Text))

Max Activating Token Index: 744

Text #4

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.2252. Min Act: -0.0003

Data Index: 964352 (C4 (Web Text))

Max Activating Token Index: 347

Text #5

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.2371. Min Act: -0.0003

Data Index: 1255953 (C4 (Web Text))

Max Activating Token Index: 591

Text #6

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.2127. Min Act: -0.0003

Data Index: 262685 (C4 (Web Text))

Max Activating Token Index: 957

Text #7

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.2050. Min Act: -0.0003

Data Index: 143093 (C4 (Web Text))

Max Activating Token Index: 600

Text #8

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.1953. Min Act: -0.0003

Data Index: 1243130 (C4 (Web Text))

Max Activating Token Index: 288

Text #9

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.2100. Min Act: -0.0003

Data Index: 614858 (C4 (Web Text))

Max Activating Token Index: 362

Text #10

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.2087. Min Act: -0.0003

Data Index: 805940 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.2157. Min Act: -0.0003

Data Index: 373277 (C4 (Web Text))

Max Activating Token Index: 705

Text #12

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.2480. Min Act: -0.0003

Data Index: 902352 (C4 (Web Text))

Max Activating Token Index: 283

Text #13

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.1839. Min Act: -0.0003

Data Index: 518748 (C4 (Web Text))

Max Activating Token Index: 655

Text #14

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.2100. Min Act: -0.0003

Data Index: 714149 (C4 (Web Text))

Max Activating Token Index: 587

Text #15

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.1961. Min Act: -0.0003

Data Index: 1289962 (C4 (Web Text))

Max Activating Token Index: 146

Text #16

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.1896. Min Act: -0.0003

Data Index: 790066 (C4 (Web Text))

Max Activating Token Index: 54

Text #17

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.2177. Min Act: -0.0003

Data Index: 1319453 (C4 (Web Text))

Max Activating Token Index: 859

Text #18

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.1975. Min Act: -0.0003

Data Index: 117528 (C4 (Web Text))

Max Activating Token Index: 27

Text #19

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.1769. Min Act: -0.0003

Data Index: 821373 (C4 (Web Text))

Max Activating Token Index: 601