Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 262 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0405. Min Act: -0.0003

Data Index: 1264408 (C4 (Web Text))

Max Activating Token Index: 294

Text #1

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0370. Min Act: -0.0004

Data Index: 61804 (C4 (Web Text))

Max Activating Token Index: 308

Text #2

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0353. Min Act: -0.0003

Data Index: 599444 (C4 (Web Text))

Max Activating Token Index: 596

Text #3

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0349. Min Act: -0.0003

Data Index: 1279202 (C4 (Web Text))

Max Activating Token Index: 364

Text #4

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0326. Min Act: -0.0004

Data Index: 260584 (C4 (Web Text))

Max Activating Token Index: 885

Text #5

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0340. Min Act: -0.0003

Data Index: 349903 (C4 (Web Text))

Max Activating Token Index: 478

Text #6

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0330. Min Act: -0.0003

Data Index: 268060 (C4 (Web Text))

Max Activating Token Index: 440

Text #7

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0316. Min Act: -0.0003

Data Index: 581031 (C4 (Web Text))

Max Activating Token Index: 844

Text #8

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0324. Min Act: -0.0003

Data Index: 1248874 (C4 (Web Text))

Max Activating Token Index: 1001

Text #9

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0318. Min Act: -0.0003

Data Index: 73417 (C4 (Web Text))

Max Activating Token Index: 150

Text #10

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0326. Min Act: -0.0003

Data Index: 1082169 (C4 (Web Text))

Max Activating Token Index: 866

Text #11

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0329. Min Act: -0.0003

Data Index: 1027240 (C4 (Web Text))

Max Activating Token Index: 1003

Text #12

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0340. Min Act: -0.0003

Data Index: 332848 (C4 (Web Text))

Max Activating Token Index: 899

Text #13

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0326. Min Act: -0.0003

Data Index: 479117 (C4 (Web Text))

Max Activating Token Index: 374

Text #14

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0314. Min Act: -0.0003

Data Index: 1276685 (C4 (Web Text))

Max Activating Token Index: 418

Text #15

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0323. Min Act: -0.0004

Data Index: 150485 (C4 (Web Text))

Max Activating Token Index: 701

Text #16

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0316. Min Act: -0.0003

Data Index: 559441 (C4 (Web Text))

Max Activating Token Index: 861

Text #17

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0304. Min Act: -0.0003

Data Index: 726287 (C4 (Web Text))

Max Activating Token Index: 896

Text #18

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0303. Min Act: -0.0003

Data Index: 289647 (C4 (Web Text))

Max Activating Token Index: 431

Text #19

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0307. Min Act: -0.0004

Data Index: 1359313 (C4 (Web Text))

Max Activating Token Index: 934