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

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

Neuron 2829 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7471. Min Range: -0.7471

Max Act: 0.7471. Min Act: -0.0001

Data Index: 649972 (C4 (Web Text))

Max Activating Token Index: 942

Text #1

Max Range: 0.7471. Min Range: -0.7471

Max Act: 0.7368. Min Act: -0.0001

Data Index: 354405 (C4 (Web Text))

Max Activating Token Index: 452

Text #2

Max Range: 0.7471. Min Range: -0.7471

Max Act: 0.6431. Min Act: -0.0001

Data Index: 447047 (C4 (Web Text))

Max Activating Token Index: 10

Text #3

Max Range: 0.7471. Min Range: -0.7471

Max Act: 0.6689. Min Act: -0.0001

Data Index: 1175507 (C4 (Web Text))

Max Activating Token Index: 879

Text #4

Max Range: 0.7471. Min Range: -0.7471

Max Act: 0.6713. Min Act: -0.0002

Data Index: 574005 (C4 (Web Text))

Max Activating Token Index: 923

Text #5

Max Range: 0.7471. Min Range: -0.7471

Max Act: 0.6338. Min Act: -0.0002

Data Index: 1349746 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 0.7471. Min Range: -0.7471

Max Act: 0.6626. Min Act: -0.0002

Data Index: 828048 (C4 (Web Text))

Max Activating Token Index: 371

Text #7

Max Range: 0.7471. Min Range: -0.7471

Max Act: 0.6454. Min Act: -0.0001

Data Index: 347259 (C4 (Web Text))

Max Activating Token Index: 129

Text #8

Max Range: 0.7471. Min Range: -0.7471

Max Act: 0.6238. Min Act: -0.0002

Data Index: 1338176 (C4 (Web Text))

Max Activating Token Index: 405

Text #9

Max Range: 0.7471. Min Range: -0.7471

Max Act: 0.6521. Min Act: -0.0001

Data Index: 991677 (C4 (Web Text))

Max Activating Token Index: 802

Text #10

Max Range: 0.7471. Min Range: -0.7471

Max Act: 0.6269. Min Act: -0.0001

Data Index: 1276811 (C4 (Web Text))

Max Activating Token Index: 452

Text #11

Max Range: 0.7471. Min Range: -0.7471

Max Act: 0.6421. Min Act: -0.0002

Data Index: 423687 (C4 (Web Text))

Max Activating Token Index: 667

Text #12

Max Range: 0.7471. Min Range: -0.7471

Max Act: 0.6165. Min Act: -0.0001

Data Index: 1003385 (C4 (Web Text))

Max Activating Token Index: 14

Text #13

Max Range: 0.7471. Min Range: -0.7471

Max Act: 0.6272. Min Act: -0.0002

Data Index: 693584 (C4 (Web Text))

Max Activating Token Index: 348

Text #14

Max Range: 0.7471. Min Range: -0.7471

Max Act: 0.5933. Min Act: -0.0001

Data Index: 1209629 (C4 (Web Text))

Max Activating Token Index: 1011

Text #15

Max Range: 0.7471. Min Range: -0.7471

Max Act: 0.6330. Min Act: -0.0001

Data Index: 238417 (C4 (Web Text))

Max Activating Token Index: 742

Text #16

Max Range: 0.7471. Min Range: -0.7471

Max Act: 0.6300. Min Act: -0.0002

Data Index: 47604 (C4 (Web Text))

Max Activating Token Index: 628

Text #17

Max Range: 0.7471. Min Range: -0.7471

Max Act: 0.6003. Min Act: -0.0001

Data Index: 93004 (C4 (Web Text))

Max Activating Token Index: 685

Text #18

Max Range: 0.7471. Min Range: -0.7471

Max Act: 0.6262. Min Act: -0.0001

Data Index: 1024409 (C4 (Web Text))

Max Activating Token Index: 549

Text #19

Max Range: 0.7471. Min Range: -0.7471

Max Act: 0.6077. Min Act: -0.0002

Data Index: 1060747 (C4 (Web Text))

Max Activating Token Index: 120