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

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

Neuron 5115 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3715. Min Range: -3.3715

Max Act: 3.3715. Min Act: -0.0000

Data Index: 874171 (C4 (Web Text))

Max Activating Token Index: 483

Text #1

Max Range: 3.3715. Min Range: -3.3715

Max Act: 2.8986. Min Act: -0.0000

Data Index: 560314 (C4 (Web Text))

Max Activating Token Index: 841

Text #2

Max Range: 3.3715. Min Range: -3.3715

Max Act: 2.9238. Min Act: -0.0000

Data Index: 1188510 (C4 (Web Text))

Max Activating Token Index: 409

Text #3

Max Range: 3.3715. Min Range: -3.3715

Max Act: 2.7878. Min Act: -0.0000

Data Index: 1288754 (C4 (Web Text))

Max Activating Token Index: 337

Text #4

Max Range: 3.3715. Min Range: -3.3715

Max Act: 3.0299. Min Act: -0.0000

Data Index: 1121128 (C4 (Web Text))

Max Activating Token Index: 162

Text #5

Max Range: 3.3715. Min Range: -3.3715

Max Act: 2.7231. Min Act: -0.0000

Data Index: 610999 (C4 (Web Text))

Max Activating Token Index: 548

Text #6

Max Range: 3.3715. Min Range: -3.3715

Max Act: 2.8335. Min Act: -0.0000

Data Index: 576408 (C4 (Web Text))

Max Activating Token Index: 316

Text #7

Max Range: 3.3715. Min Range: -3.3715

Max Act: 3.0038. Min Act: -0.0000

Data Index: 886891 (C4 (Web Text))

Max Activating Token Index: 901

Text #8

Max Range: 3.3715. Min Range: -3.3715

Max Act: 2.5503. Min Act: -0.0000

Data Index: 1193009 (C4 (Web Text))

Max Activating Token Index: 307

Text #9

Max Range: 3.3715. Min Range: -3.3715

Max Act: 2.7673. Min Act: -0.0000

Data Index: 782290 (C4 (Web Text))

Max Activating Token Index: 246

Text #10

Max Range: 3.3715. Min Range: -3.3715

Max Act: 2.4890. Min Act: -0.0000

Data Index: 313479 (C4 (Web Text))

Max Activating Token Index: 952

Text #11

Max Range: 3.3715. Min Range: -3.3715

Max Act: 2.4557. Min Act: -0.0000

Data Index: 934296 (C4 (Web Text))

Max Activating Token Index: 173

Text #12

Max Range: 3.3715. Min Range: -3.3715

Max Act: 2.5984. Min Act: -0.0000

Data Index: 190313 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 3.3715. Min Range: -3.3715

Max Act: 2.4264. Min Act: -0.0000

Data Index: 1028138 (C4 (Web Text))

Max Activating Token Index: 566

Text #14

Max Range: 3.3715. Min Range: -3.3715

Max Act: 2.4061. Min Act: -0.0000

Data Index: 1206643 (C4 (Web Text))

Max Activating Token Index: 346

Text #15

Max Range: 3.3715. Min Range: -3.3715

Max Act: 2.4885. Min Act: -0.0000

Data Index: 579554 (C4 (Web Text))

Max Activating Token Index: 928

Text #16

Max Range: 3.3715. Min Range: -3.3715

Max Act: 2.3339. Min Act: -0.0000

Data Index: 33004 (C4 (Web Text))

Max Activating Token Index: 848

Text #17

Max Range: 3.3715. Min Range: -3.3715

Max Act: 2.4605. Min Act: -0.0000

Data Index: 724361 (C4 (Web Text))

Max Activating Token Index: 1006

Text #18

Max Range: 3.3715. Min Range: -3.3715

Max Act: 2.4042. Min Act: -0.0000

Data Index: 689315 (C4 (Web Text))

Max Activating Token Index: 479

Text #19

Max Range: 3.3715. Min Range: -3.3715

Max Act: 2.3719. Min Act: -0.0000

Data Index: 480531 (C4 (Web Text))

Max Activating Token Index: 869