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

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

Neuron 5015 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: 0.8311. Min Range: -0.8311

Max Act: 0.8311. Min Act: -0.0001

Data Index: 1228266 (C4 (Web Text))

Max Activating Token Index: 796

Text #1

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.8061. Min Act: -0.0001

Data Index: 673025 (C4 (Web Text))

Max Activating Token Index: 763

Text #2

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.7452. Min Act: -0.0001

Data Index: 1241364 (C4 (Web Text))

Max Activating Token Index: 302

Text #3

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.7136. Min Act: -0.0001

Data Index: 375133 (C4 (Web Text))

Max Activating Token Index: 600

Text #4

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.6941. Min Act: -0.0001

Data Index: 242761 (C4 (Web Text))

Max Activating Token Index: 289

Text #5

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.6978. Min Act: -0.0000

Data Index: 820923 (C4 (Web Text))

Max Activating Token Index: 490

Text #6

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.6924. Min Act: -0.0001

Data Index: 1188071 (C4 (Web Text))

Max Activating Token Index: 532

Text #7

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.6947. Min Act: -0.0001

Data Index: 354546 (C4 (Web Text))

Max Activating Token Index: 541

Text #8

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.7441. Min Act: -0.0001

Data Index: 605909 (C4 (Web Text))

Max Activating Token Index: 806

Text #9

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.7287. Min Act: -0.0001

Data Index: 749994 (C4 (Web Text))

Max Activating Token Index: 929

Text #10

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.7201. Min Act: -0.0001

Data Index: 675341 (C4 (Web Text))

Max Activating Token Index: 585

Text #11

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.6927. Min Act: -0.0000

Data Index: 488310 (C4 (Web Text))

Max Activating Token Index: 929

Text #12

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.6004. Min Act: -0.0001

Data Index: 507355 (C4 (Web Text))

Max Activating Token Index: 809

Text #13

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.7514. Min Act: -0.0001

Data Index: 75014 (C4 (Web Text))

Max Activating Token Index: 211

Text #14

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.6451. Min Act: -0.0001

Data Index: 322545 (C4 (Web Text))

Max Activating Token Index: 183

Text #15

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.6651. Min Act: -0.0001

Data Index: 841965 (C4 (Web Text))

Max Activating Token Index: 565

Text #16

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.6493. Min Act: -0.0001

Data Index: 1051428 (C4 (Web Text))

Max Activating Token Index: 309

Text #17

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.6538. Min Act: -0.0000

Data Index: 378693 (C4 (Web Text))

Max Activating Token Index: 734

Text #18

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.6333. Min Act: -0.0001

Data Index: 199758 (C4 (Web Text))

Max Activating Token Index: 960

Text #19

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.6341. Min Act: -0.0001

Data Index: 1182706 (C4 (Web Text))

Max Activating Token Index: 371