Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 419 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.4969. Min Range: -3.4969

Max Act: 3.4969. Min Act: -0.0000

Data Index: 887919 (C4 (Web Text))

Max Activating Token Index: 86

Text #1

Max Range: 3.4969. Min Range: -3.4969

Max Act: 3.2844. Min Act: -0.0000

Data Index: 254187 (C4 (Web Text))

Max Activating Token Index: 907

Text #2

Max Range: 3.4969. Min Range: -3.4969

Max Act: 2.7198. Min Act: -0.0000

Data Index: 258649 (C4 (Web Text))

Max Activating Token Index: 188

Text #3

Max Range: 3.4969. Min Range: -3.4969

Max Act: 2.6912. Min Act: 0.0000

Data Index: 611145 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 3.4969. Min Range: -3.4969

Max Act: 2.6572. Min Act: -0.0000

Data Index: 65772 (C4 (Web Text))

Max Activating Token Index: 371

Text #5

Max Range: 3.4969. Min Range: -3.4969

Max Act: 2.6315. Min Act: -0.0001

Data Index: 245626 (C4 (Web Text))

Max Activating Token Index: 448

Text #6

Max Range: 3.4969. Min Range: -3.4969

Max Act: 2.5948. Min Act: -0.0000

Data Index: 627227 (C4 (Web Text))

Max Activating Token Index: 870

Text #7

Max Range: 3.4969. Min Range: -3.4969

Max Act: 2.4544. Min Act: -0.0000

Data Index: 722338 (C4 (Web Text))

Max Activating Token Index: 242

Text #8

Max Range: 3.4969. Min Range: -3.4969

Max Act: 2.5545. Min Act: -0.0000

Data Index: 209388 (C4 (Web Text))

Max Activating Token Index: 144

Text #9

Max Range: 3.4969. Min Range: -3.4969

Max Act: 2.4405. Min Act: -0.0000

Data Index: 96312 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 3.4969. Min Range: -3.4969

Max Act: 2.4186. Min Act: -0.0000

Data Index: 115853 (C4 (Web Text))

Max Activating Token Index: 414

Text #11

Max Range: 3.4969. Min Range: -3.4969

Max Act: 2.5367. Min Act: -0.0000

Data Index: 993065 (C4 (Web Text))

Max Activating Token Index: 569

Text #12

Max Range: 3.4969. Min Range: -3.4969

Max Act: 2.3833. Min Act: -0.0000

Data Index: 700621 (C4 (Web Text))

Max Activating Token Index: 153

Text #13

Max Range: 3.4969. Min Range: -3.4969

Max Act: 2.3633. Min Act: -0.0000

Data Index: 488318 (C4 (Web Text))

Max Activating Token Index: 36

Text #14

Max Range: 3.4969. Min Range: -3.4969

Max Act: 2.3617. Min Act: -0.0000

Data Index: 756230 (C4 (Web Text))

Max Activating Token Index: 465

Text #15

Max Range: 3.4969. Min Range: -3.4969

Max Act: 2.3575. Min Act: -0.0000

Data Index: 1144359 (C4 (Web Text))

Max Activating Token Index: 280

Text #16

Max Range: 3.4969. Min Range: -3.4969

Max Act: 2.3424. Min Act: -0.0000

Data Index: 85606 (C4 (Web Text))

Max Activating Token Index: 80

Text #17

Max Range: 3.4969. Min Range: -3.4969

Max Act: 2.4558. Min Act: -0.0000

Data Index: 802746 (C4 (Web Text))

Max Activating Token Index: 239

Text #18

Max Range: 3.4969. Min Range: -3.4969

Max Act: 2.3298. Min Act: -0.0000

Data Index: 1165448 (C4 (Web Text))

Max Activating Token Index: 65

Text #19

Max Range: 3.4969. Min Range: -3.4969

Max Act: 2.3265. Min Act: -0.0000

Data Index: 1324363 (C4 (Web Text))

Max Activating Token Index: 657