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

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

Neuron 4407 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4596. Min Range: -0.4596

Max Act: 0.4596. Min Act: -0.0000

Data Index: 1344496 (C4 (Web Text))

Max Activating Token Index: 709

Text #1

Max Range: 0.4596. Min Range: -0.4596

Max Act: 0.4026. Min Act: -0.0000

Data Index: 4606 (C4 (Web Text))

Max Activating Token Index: 243

Text #2

Max Range: 0.4596. Min Range: -0.4596

Max Act: 0.3895. Min Act: -0.0000

Data Index: 385479 (C4 (Web Text))

Max Activating Token Index: 994

Text #3

Max Range: 0.4596. Min Range: -0.4596

Max Act: 0.4041. Min Act: -0.0000

Data Index: 1301547 (C4 (Web Text))

Max Activating Token Index: 252

Text #4

Max Range: 0.4596. Min Range: -0.4596

Max Act: 0.3912. Min Act: -0.0000

Data Index: 297306 (C4 (Web Text))

Max Activating Token Index: 231

Text #5

Max Range: 0.4596. Min Range: -0.4596

Max Act: 0.3819. Min Act: -0.0000

Data Index: 1350441 (C4 (Web Text))

Max Activating Token Index: 333

Text #6

Max Range: 0.4596. Min Range: -0.4596

Max Act: 0.3808. Min Act: -0.0000

Data Index: 581399 (C4 (Web Text))

Max Activating Token Index: 42

Text #7

Max Range: 0.4596. Min Range: -0.4596

Max Act: 0.3644. Min Act: -0.0000

Data Index: 838404 (C4 (Web Text))

Max Activating Token Index: 533

Text #8

Max Range: 0.4596. Min Range: -0.4596

Max Act: 0.3492. Min Act: -0.0000

Data Index: 1345981 (C4 (Web Text))

Max Activating Token Index: 560

Text #9

Max Range: 0.4596. Min Range: -0.4596

Max Act: 0.3418. Min Act: -0.0000

Data Index: 711583 (C4 (Web Text))

Max Activating Token Index: 642

Text #10

Max Range: 0.4596. Min Range: -0.4596

Max Act: 0.3413. Min Act: -0.0000

Data Index: 270331 (C4 (Web Text))

Max Activating Token Index: 912

Text #11

Max Range: 0.4596. Min Range: -0.4596

Max Act: 0.3432. Min Act: -0.0000

Data Index: 1324272 (C4 (Web Text))

Max Activating Token Index: 657

Text #12

Max Range: 0.4596. Min Range: -0.4596

Max Act: 0.3238. Min Act: -0.0000

Data Index: 290145 (C4 (Web Text))

Max Activating Token Index: 375

Text #13

Max Range: 0.4596. Min Range: -0.4596

Max Act: 0.3214. Min Act: -0.0000

Data Index: 805090 (C4 (Web Text))

Max Activating Token Index: 280

Text #14

Max Range: 0.4596. Min Range: -0.4596

Max Act: 0.3265. Min Act: -0.0000

Data Index: 832179 (C4 (Web Text))

Max Activating Token Index: 921

Text #15

Max Range: 0.4596. Min Range: -0.4596

Max Act: 0.3245. Min Act: -0.0000

Data Index: 966085 (C4 (Web Text))

Max Activating Token Index: 469

Text #16

Max Range: 0.4596. Min Range: -0.4596

Max Act: 0.3166. Min Act: -0.0000

Data Index: 1337693 (C4 (Web Text))

Max Activating Token Index: 399

Text #17

Max Range: 0.4596. Min Range: -0.4596

Max Act: 0.3056. Min Act: -0.0000

Data Index: 258681 (C4 (Web Text))

Max Activating Token Index: 476

Text #18

Max Range: 0.4596. Min Range: -0.4596

Max Act: 0.3218. Min Act: -0.0000

Data Index: 1048433 (C4 (Web Text))

Max Activating Token Index: 1017

Text #19

Max Range: 0.4596. Min Range: -0.4596

Max Act: 0.3105. Min Act: -0.0000

Data Index: 102351 (C4 (Web Text))

Max Activating Token Index: 536