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

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

Neuron 5205 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0542. Min Act: -0.0001

Data Index: 1073315 (C4 (Web Text))

Max Activating Token Index: 266

Text #1

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0544. Min Act: -0.0001

Data Index: 1600758 (Python Code)

Max Activating Token Index: 582

Text #2

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0498. Min Act: -0.0000

Data Index: 1223638 (C4 (Web Text))

Max Activating Token Index: 273

Text #3

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0490. Min Act: -0.0001

Data Index: 254754 (C4 (Web Text))

Max Activating Token Index: 255

Text #4

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0525. Min Act: -0.0001

Data Index: 1142372 (C4 (Web Text))

Max Activating Token Index: 102

Text #5

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0500. Min Act: -0.0001

Data Index: 1399794 (Python Code)

Max Activating Token Index: 286

Text #6

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0466. Min Act: -0.0001

Data Index: 480239 (C4 (Web Text))

Max Activating Token Index: 74

Text #7

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0503. Min Act: -0.0001

Data Index: 47504 (C4 (Web Text))

Max Activating Token Index: 842

Text #8

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0508. Min Act: -0.0001

Data Index: 1071538 (C4 (Web Text))

Max Activating Token Index: 326

Text #9

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0480. Min Act: -0.0001

Data Index: 1183718 (C4 (Web Text))

Max Activating Token Index: 657

Text #10

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0507. Min Act: -0.0001

Data Index: 84841 (C4 (Web Text))

Max Activating Token Index: 279

Text #11

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0488. Min Act: -0.0001

Data Index: 312389 (C4 (Web Text))

Max Activating Token Index: 328

Text #12

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0503. Min Act: -0.0001

Data Index: 879365 (C4 (Web Text))

Max Activating Token Index: 626

Text #13

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0467. Min Act: -0.0001

Data Index: 809407 (C4 (Web Text))

Max Activating Token Index: 548

Text #14

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0476. Min Act: -0.0000

Data Index: 308745 (C4 (Web Text))

Max Activating Token Index: 206

Text #15

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0493. Min Act: -0.0001

Data Index: 741056 (C4 (Web Text))

Max Activating Token Index: 578

Text #16

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0461. Min Act: -0.0001

Data Index: 1637249 (Python Code)

Max Activating Token Index: 756

Text #17

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0448. Min Act: -0.0001

Data Index: 116375 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0462. Min Act: -0.0000

Data Index: 229297 (C4 (Web Text))

Max Activating Token Index: 97

Text #19

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0463. Min Act: -0.0001

Data Index: 744287 (C4 (Web Text))

Max Activating Token Index: 853