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

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

Neuron 450 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0590. Min Act: -0.0002

Data Index: 554237 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0527. Min Act: -0.0002

Data Index: 815040 (C4 (Web Text))

Max Activating Token Index: 556

Text #2

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0515. Min Act: -0.0003

Data Index: 93046 (C4 (Web Text))

Max Activating Token Index: 774

Text #3

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0487. Min Act: -0.0002

Data Index: 438409 (C4 (Web Text))

Max Activating Token Index: 278

Text #4

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0476. Min Act: -0.0003

Data Index: 709651 (C4 (Web Text))

Max Activating Token Index: 68

Text #5

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0480. Min Act: -0.0002

Data Index: 1342424 (C4 (Web Text))

Max Activating Token Index: 185

Text #6

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0453. Min Act: -0.0003

Data Index: 467342 (C4 (Web Text))

Max Activating Token Index: 593

Text #7

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0471. Min Act: -0.0002

Data Index: 1176233 (C4 (Web Text))

Max Activating Token Index: 555

Text #8

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0450. Min Act: -0.0002

Data Index: 680049 (C4 (Web Text))

Max Activating Token Index: 167

Text #9

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0459. Min Act: -0.0003

Data Index: 1110056 (C4 (Web Text))

Max Activating Token Index: 208

Text #10

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0456. Min Act: -0.0002

Data Index: 1240895 (C4 (Web Text))

Max Activating Token Index: 949

Text #11

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0437. Min Act: -0.0002

Data Index: 834289 (C4 (Web Text))

Max Activating Token Index: 713

Text #12

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0438. Min Act: -0.0003

Data Index: 370099 (C4 (Web Text))

Max Activating Token Index: 987

Text #13

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0457. Min Act: -0.0002

Data Index: 210592 (C4 (Web Text))

Max Activating Token Index: 859

Text #14

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0442. Min Act: -0.0003

Data Index: 600455 (C4 (Web Text))

Max Activating Token Index: 402

Text #15

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0441. Min Act: -0.0003

Data Index: 430215 (C4 (Web Text))

Max Activating Token Index: 835

Text #16

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0430. Min Act: -0.0002

Data Index: 1155710 (C4 (Web Text))

Max Activating Token Index: 286

Text #17

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0441. Min Act: -0.0002

Data Index: 1023249 (C4 (Web Text))

Max Activating Token Index: 824

Text #18

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0410. Min Act: -0.0003

Data Index: 790750 (C4 (Web Text))

Max Activating Token Index: 758

Text #19

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0427. Min Act: -0.0002

Data Index: 78417 (C4 (Web Text))

Max Activating Token Index: 818