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

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

Neuron 4231 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: 6.6410. Min Range: -6.6410

Max Act: 6.2526. Min Act: -0.0000

Data Index: 228282 (C4 (Web Text))

Max Activating Token Index: 275

Text #1

Max Range: 6.6410. Min Range: -6.6410

Max Act: 6.4999. Min Act: -0.0000

Data Index: 1077351 (C4 (Web Text))

Max Activating Token Index: 417

Text #2

Max Range: 6.6410. Min Range: -6.6410

Max Act: 6.6410. Min Act: -0.0000

Data Index: 824476 (C4 (Web Text))

Max Activating Token Index: 326

Text #3

Max Range: 6.6410. Min Range: -6.6410

Max Act: 6.4292. Min Act: -0.0000

Data Index: 860602 (C4 (Web Text))

Max Activating Token Index: 224

Text #4

Max Range: 6.6410. Min Range: -6.6410

Max Act: 6.6312. Min Act: -0.0000

Data Index: 59029 (C4 (Web Text))

Max Activating Token Index: 433

Text #5

Max Range: 6.6410. Min Range: -6.6410

Max Act: 6.4254. Min Act: -0.0000

Data Index: 83128 (C4 (Web Text))

Max Activating Token Index: 340

Text #6

Max Range: 6.6410. Min Range: -6.6410

Max Act: 6.3927. Min Act: -0.0000

Data Index: 818146 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 6.6410. Min Range: -6.6410

Max Act: 6.3658. Min Act: -0.0000

Data Index: 1344666 (C4 (Web Text))

Max Activating Token Index: 916

Text #8

Max Range: 6.6410. Min Range: -6.6410

Max Act: 6.5013. Min Act: -0.0000

Data Index: 906384 (C4 (Web Text))

Max Activating Token Index: 567

Text #9

Max Range: 6.6410. Min Range: -6.6410

Max Act: 6.4805. Min Act: -0.0000

Data Index: 268408 (C4 (Web Text))

Max Activating Token Index: 414

Text #10

Max Range: 6.6410. Min Range: -6.6410

Max Act: 6.2516. Min Act: -0.0000

Data Index: 379508 (C4 (Web Text))

Max Activating Token Index: 268

Text #11

Max Range: 6.6410. Min Range: -6.6410

Max Act: 6.4906. Min Act: -0.0000

Data Index: 181438 (C4 (Web Text))

Max Activating Token Index: 297

Text #12

Max Range: 6.6410. Min Range: -6.6410

Max Act: 6.2684. Min Act: -0.0000

Data Index: 653173 (C4 (Web Text))

Max Activating Token Index: 476

Text #13

Max Range: 6.6410. Min Range: -6.6410

Max Act: 6.6317. Min Act: -0.0000

Data Index: 1344668 (C4 (Web Text))

Max Activating Token Index: 327

Text #14

Max Range: 6.6410. Min Range: -6.6410

Max Act: 6.4449. Min Act: -0.0000

Data Index: 1065786 (C4 (Web Text))

Max Activating Token Index: 534

Text #15

Max Range: 6.6410. Min Range: -6.6410

Max Act: 6.4631. Min Act: -0.0000

Data Index: 17513 (C4 (Web Text))

Max Activating Token Index: 522

Text #16

Max Range: 6.6410. Min Range: -6.6410

Max Act: 6.3135. Min Act: -0.0000

Data Index: 1044012 (C4 (Web Text))

Max Activating Token Index: 323

Text #17

Max Range: 6.6410. Min Range: -6.6410

Max Act: 6.4439. Min Act: -0.0000

Data Index: 58532 (C4 (Web Text))

Max Activating Token Index: 450

Text #18

Max Range: 6.6410. Min Range: -6.6410

Max Act: 6.0968. Min Act: -0.0000

Data Index: 628632 (C4 (Web Text))

Max Activating Token Index: 347

Text #19

Max Range: 6.6410. Min Range: -6.6410

Max Act: 6.2916. Min Act: -0.0000

Data Index: 1078904 (C4 (Web Text))

Max Activating Token Index: 502