Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 185 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7964. Min Range: -0.7964

Max Act: 0.7964. Min Act: -0.0001

Data Index: 1170035 (C4 (Web Text))

Max Activating Token Index: 899

Text #1

Max Range: 0.7964. Min Range: -0.7964

Max Act: 0.5697. Min Act: -0.0001

Data Index: 772400 (C4 (Web Text))

Max Activating Token Index: 573

Text #2

Max Range: 0.7964. Min Range: -0.7964

Max Act: 0.6369. Min Act: -0.0001

Data Index: 775101 (C4 (Web Text))

Max Activating Token Index: 554

Text #3

Max Range: 0.7964. Min Range: -0.7964

Max Act: 0.5795. Min Act: -0.0001

Data Index: 703656 (C4 (Web Text))

Max Activating Token Index: 338

Text #4

Max Range: 0.7964. Min Range: -0.7964

Max Act: 0.5295. Min Act: -0.0001

Data Index: 1256298 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 0.7964. Min Range: -0.7964

Max Act: 0.5382. Min Act: -0.0001

Data Index: 1174403 (C4 (Web Text))

Max Activating Token Index: 780

Text #6

Max Range: 0.7964. Min Range: -0.7964

Max Act: 0.5209. Min Act: -0.0001

Data Index: 1029287 (C4 (Web Text))

Max Activating Token Index: 465

Text #7

Max Range: 0.7964. Min Range: -0.7964

Max Act: 0.4493. Min Act: -0.0001

Data Index: 44685 (C4 (Web Text))

Max Activating Token Index: 569

Text #8

Max Range: 0.7964. Min Range: -0.7964

Max Act: 0.4777. Min Act: -0.0001

Data Index: 1292954 (C4 (Web Text))

Max Activating Token Index: 760

Text #9

Max Range: 0.7964. Min Range: -0.7964

Max Act: 0.5026. Min Act: -0.0001

Data Index: 675453 (C4 (Web Text))

Max Activating Token Index: 930

Text #10

Max Range: 0.7964. Min Range: -0.7964

Max Act: 0.5144. Min Act: -0.0001

Data Index: 171019 (C4 (Web Text))

Max Activating Token Index: 723

Text #11

Max Range: 0.7964. Min Range: -0.7964

Max Act: 0.4830. Min Act: -0.0001

Data Index: 254396 (C4 (Web Text))

Max Activating Token Index: 471

Text #12

Max Range: 0.7964. Min Range: -0.7964

Max Act: 0.5280. Min Act: -0.0001

Data Index: 287938 (C4 (Web Text))

Max Activating Token Index: 632

Text #13

Max Range: 0.7964. Min Range: -0.7964

Max Act: 0.4693. Min Act: -0.0001

Data Index: 112643 (C4 (Web Text))

Max Activating Token Index: 409

Text #14

Max Range: 0.7964. Min Range: -0.7964

Max Act: 0.5043. Min Act: -0.0001

Data Index: 549389 (C4 (Web Text))

Max Activating Token Index: 413

Text #15

Max Range: 0.7964. Min Range: -0.7964

Max Act: 0.4383. Min Act: -0.0001

Data Index: 1653613 (Python Code)

Max Activating Token Index: 430

Text #16

Max Range: 0.7964. Min Range: -0.7964

Max Act: 0.4933. Min Act: -0.0001

Data Index: 574559 (C4 (Web Text))

Max Activating Token Index: 1006

Text #17

Max Range: 0.7964. Min Range: -0.7964

Max Act: 0.4782. Min Act: -0.0001

Data Index: 888661 (C4 (Web Text))

Max Activating Token Index: 488

Text #18

Max Range: 0.7964. Min Range: -0.7964

Max Act: 0.4913. Min Act: -0.0001

Data Index: 691376 (C4 (Web Text))

Max Activating Token Index: 155

Text #19

Max Range: 0.7964. Min Range: -0.7964

Max Act: 0.4738. Min Act: -0.0001

Data Index: 154081 (C4 (Web Text))

Max Activating Token Index: 553