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

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

Neuron 3806 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5779. Min Range: -0.5779

Max Act: 0.5779. Min Act: -0.0000

Data Index: 1299013 (C4 (Web Text))

Max Activating Token Index: 434

Text #1

Max Range: 0.5779. Min Range: -0.5779

Max Act: 0.5428. Min Act: -0.0000

Data Index: 1650597 (Python Code)

Max Activating Token Index: 990

Text #2

Max Range: 0.5779. Min Range: -0.5779

Max Act: 0.5392. Min Act: -0.0000

Data Index: 887237 (C4 (Web Text))

Max Activating Token Index: 499

Text #3

Max Range: 0.5779. Min Range: -0.5779

Max Act: 0.4932. Min Act: -0.0000

Data Index: 1279352 (C4 (Web Text))

Max Activating Token Index: 342

Text #4

Max Range: 0.5779. Min Range: -0.5779

Max Act: 0.5579. Min Act: -0.0000

Data Index: 1415138 (Python Code)

Max Activating Token Index: 875

Text #5

Max Range: 0.5779. Min Range: -0.5779

Max Act: 0.4837. Min Act: -0.0000

Data Index: 539563 (C4 (Web Text))

Max Activating Token Index: 358

Text #6

Max Range: 0.5779. Min Range: -0.5779

Max Act: 0.4498. Min Act: -0.0000

Data Index: 524489 (C4 (Web Text))

Max Activating Token Index: 280

Text #7

Max Range: 0.5779. Min Range: -0.5779

Max Act: 0.4866. Min Act: -0.0000

Data Index: 473436 (C4 (Web Text))

Max Activating Token Index: 308

Text #8

Max Range: 0.5779. Min Range: -0.5779

Max Act: 0.4136. Min Act: -0.0000

Data Index: 1270198 (C4 (Web Text))

Max Activating Token Index: 539

Text #9

Max Range: 0.5779. Min Range: -0.5779

Max Act: 0.4168. Min Act: -0.0000

Data Index: 442376 (C4 (Web Text))

Max Activating Token Index: 445

Text #10

Max Range: 0.5779. Min Range: -0.5779

Max Act: 0.4133. Min Act: -0.0000

Data Index: 942988 (C4 (Web Text))

Max Activating Token Index: 154

Text #11

Max Range: 0.5779. Min Range: -0.5779

Max Act: 0.4257. Min Act: -0.0000

Data Index: 730092 (C4 (Web Text))

Max Activating Token Index: 33

Text #12

Max Range: 0.5779. Min Range: -0.5779

Max Act: 0.4147. Min Act: -0.0000

Data Index: 288787 (C4 (Web Text))

Max Activating Token Index: 653

Text #13

Max Range: 0.5779. Min Range: -0.5779

Max Act: 0.4450. Min Act: -0.0000

Data Index: 862957 (C4 (Web Text))

Max Activating Token Index: 717

Text #14

Max Range: 0.5779. Min Range: -0.5779

Max Act: 0.4148. Min Act: -0.0000

Data Index: 15650 (C4 (Web Text))

Max Activating Token Index: 576

Text #15

Max Range: 0.5779. Min Range: -0.5779

Max Act: 0.4440. Min Act: -0.0000

Data Index: 396759 (C4 (Web Text))

Max Activating Token Index: 268

Text #16

Max Range: 0.5779. Min Range: -0.5779

Max Act: 0.4264. Min Act: -0.0000

Data Index: 1266406 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 0.5779. Min Range: -0.5779

Max Act: 0.4225. Min Act: -0.0000

Data Index: 182454 (C4 (Web Text))

Max Activating Token Index: 57

Text #18

Max Range: 0.5779. Min Range: -0.5779

Max Act: 0.4233. Min Act: -0.0000

Data Index: 63531 (C4 (Web Text))

Max Activating Token Index: 470

Text #19

Max Range: 0.5779. Min Range: -0.5779

Max Act: 0.4342. Min Act: -0.0000

Data Index: 566248 (C4 (Web Text))

Max Activating Token Index: 1016