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

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

Neuron 3214 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2348. Min Range: -3.2348

Max Act: 3.2348. Min Act: -0.0001

Data Index: 631798 (C4 (Web Text))

Max Activating Token Index: 358

Text #1

Max Range: 3.2348. Min Range: -3.2348

Max Act: 2.9484. Min Act: -0.0000

Data Index: 550459 (C4 (Web Text))

Max Activating Token Index: 911

Text #2

Max Range: 3.2348. Min Range: -3.2348

Max Act: 2.6507. Min Act: -0.0001

Data Index: 1051824 (C4 (Web Text))

Max Activating Token Index: 157

Text #3

Max Range: 3.2348. Min Range: -3.2348

Max Act: 2.8525. Min Act: -0.0001

Data Index: 1189828 (C4 (Web Text))

Max Activating Token Index: 566

Text #4

Max Range: 3.2348. Min Range: -3.2348

Max Act: 2.8198. Min Act: -0.0001

Data Index: 61136 (C4 (Web Text))

Max Activating Token Index: 411

Text #5

Max Range: 3.2348. Min Range: -3.2348

Max Act: 2.4332. Min Act: -0.0001

Data Index: 392405 (C4 (Web Text))

Max Activating Token Index: 514

Text #6

Max Range: 3.2348. Min Range: -3.2348

Max Act: 2.8650. Min Act: -0.0001

Data Index: 546700 (C4 (Web Text))

Max Activating Token Index: 823

Text #7

Max Range: 3.2348. Min Range: -3.2348

Max Act: 2.6483. Min Act: -0.0000

Data Index: 967298 (C4 (Web Text))

Max Activating Token Index: 367

Text #8

Max Range: 3.2348. Min Range: -3.2348

Max Act: 2.5207. Min Act: -0.0000

Data Index: 771155 (C4 (Web Text))

Max Activating Token Index: 298

Text #9

Max Range: 3.2348. Min Range: -3.2348

Max Act: 2.4998. Min Act: -0.0001

Data Index: 103891 (C4 (Web Text))

Max Activating Token Index: 415

Text #10

Max Range: 3.2348. Min Range: -3.2348

Max Act: 2.4305. Min Act: -0.0001

Data Index: 992514 (C4 (Web Text))

Max Activating Token Index: 103

Text #11

Max Range: 3.2348. Min Range: -3.2348

Max Act: 2.5755. Min Act: -0.0000

Data Index: 667957 (C4 (Web Text))

Max Activating Token Index: 417

Text #12

Max Range: 3.2348. Min Range: -3.2348

Max Act: 2.5620. Min Act: -0.0001

Data Index: 1304637 (C4 (Web Text))

Max Activating Token Index: 821

Text #13

Max Range: 3.2348. Min Range: -3.2348

Max Act: 2.5729. Min Act: -0.0000

Data Index: 929306 (C4 (Web Text))

Max Activating Token Index: 86

Text #14

Max Range: 3.2348. Min Range: -3.2348

Max Act: 2.8115. Min Act: -0.0001

Data Index: 1090496 (C4 (Web Text))

Max Activating Token Index: 80

Text #15

Max Range: 3.2348. Min Range: -3.2348

Max Act: 2.8049. Min Act: -0.0001

Data Index: 336147 (C4 (Web Text))

Max Activating Token Index: 643

Text #16

Max Range: 3.2348. Min Range: -3.2348

Max Act: 2.4431. Min Act: -0.0001

Data Index: 374301 (C4 (Web Text))

Max Activating Token Index: 405

Text #17

Max Range: 3.2348. Min Range: -3.2348

Max Act: 2.4442. Min Act: -0.0001

Data Index: 43025 (C4 (Web Text))

Max Activating Token Index: 739

Text #18

Max Range: 3.2348. Min Range: -3.2348

Max Act: 2.4279. Min Act: -0.0001

Data Index: 702880 (C4 (Web Text))

Max Activating Token Index: 452

Text #19

Max Range: 3.2348. Min Range: -3.2348

Max Act: 2.5524. Min Act: -0.0000

Data Index: 174013 (C4 (Web Text))

Max Activating Token Index: 418