Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1033 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.7953. Min Range: -4.7953

Max Act: 4.6638. Min Act: -0.0000

Data Index: 558450 (C4 (Web Text))

Max Activating Token Index: 528

Text #1

Max Range: 4.7953. Min Range: -4.7953

Max Act: 4.7163. Min Act: -0.0000

Data Index: 807323 (C4 (Web Text))

Max Activating Token Index: 343

Text #2

Max Range: 4.7953. Min Range: -4.7953

Max Act: 4.6883. Min Act: -0.0000

Data Index: 1347336 (C4 (Web Text))

Max Activating Token Index: 458

Text #3

Max Range: 4.7953. Min Range: -4.7953

Max Act: 4.7953. Min Act: -0.0000

Data Index: 421907 (C4 (Web Text))

Max Activating Token Index: 955

Text #4

Max Range: 4.7953. Min Range: -4.7953

Max Act: 4.4162. Min Act: -0.0000

Data Index: 745445 (C4 (Web Text))

Max Activating Token Index: 813

Text #5

Max Range: 4.7953. Min Range: -4.7953

Max Act: 4.3438. Min Act: -0.0001

Data Index: 247917 (C4 (Web Text))

Max Activating Token Index: 618

Text #6

Max Range: 4.7953. Min Range: -4.7953

Max Act: 4.2642. Min Act: -0.0000

Data Index: 488318 (C4 (Web Text))

Max Activating Token Index: 319

Text #7

Max Range: 4.7953. Min Range: -4.7953

Max Act: 4.0396. Min Act: -0.0001

Data Index: 698483 (C4 (Web Text))

Max Activating Token Index: 946

Text #8

Max Range: 4.7953. Min Range: -4.7953

Max Act: 4.3160. Min Act: -0.0001

Data Index: 191012 (C4 (Web Text))

Max Activating Token Index: 982

Text #9

Max Range: 4.7953. Min Range: -4.7953

Max Act: 4.0068. Min Act: -0.0000

Data Index: 460128 (C4 (Web Text))

Max Activating Token Index: 601

Text #10

Max Range: 4.7953. Min Range: -4.7953

Max Act: 3.6394. Min Act: -0.0000

Data Index: 1352029 (C4 (Web Text))

Max Activating Token Index: 1020

Text #11

Max Range: 4.7953. Min Range: -4.7953

Max Act: 3.9495. Min Act: -0.0000

Data Index: 168413 (C4 (Web Text))

Max Activating Token Index: 269

Text #12

Max Range: 4.7953. Min Range: -4.7953

Max Act: 3.8069. Min Act: -0.0000

Data Index: 675021 (C4 (Web Text))

Max Activating Token Index: 530

Text #13

Max Range: 4.7953. Min Range: -4.7953

Max Act: 3.9431. Min Act: -0.0000

Data Index: 518067 (C4 (Web Text))

Max Activating Token Index: 607

Text #14

Max Range: 4.7953. Min Range: -4.7953

Max Act: 3.6122. Min Act: -0.0001

Data Index: 1317156 (C4 (Web Text))

Max Activating Token Index: 129

Text #15

Max Range: 4.7953. Min Range: -4.7953

Max Act: 3.9153. Min Act: -0.0000

Data Index: 1031974 (C4 (Web Text))

Max Activating Token Index: 601

Text #16

Max Range: 4.7953. Min Range: -4.7953

Max Act: 3.8465. Min Act: -0.0000

Data Index: 796102 (C4 (Web Text))

Max Activating Token Index: 111

Text #17

Max Range: 4.7953. Min Range: -4.7953

Max Act: 3.7638. Min Act: -0.0000

Data Index: 958835 (C4 (Web Text))

Max Activating Token Index: 340

Text #18

Max Range: 4.7953. Min Range: -4.7953

Max Act: 3.4444. Min Act: -0.0001

Data Index: 983363 (C4 (Web Text))

Max Activating Token Index: 279

Text #19

Max Range: 4.7953. Min Range: -4.7953

Max Act: 3.9283. Min Act: -0.0000

Data Index: 928950 (C4 (Web Text))

Max Activating Token Index: 252