Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1415 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0546. Min Act: -0.0002

Data Index: 122272 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0517. Min Act: -0.0002

Data Index: 1287036 (C4 (Web Text))

Max Activating Token Index: 208

Text #2

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0492. Min Act: -0.0002

Data Index: 780995 (C4 (Web Text))

Max Activating Token Index: 375

Text #3

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0489. Min Act: -0.0002

Data Index: 1056587 (C4 (Web Text))

Max Activating Token Index: 218

Text #4

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0485. Min Act: -0.0002

Data Index: 1117563 (C4 (Web Text))

Max Activating Token Index: 731

Text #5

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0494. Min Act: -0.0002

Data Index: 184818 (C4 (Web Text))

Max Activating Token Index: 849

Text #6

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0466. Min Act: -0.0002

Data Index: 1077484 (C4 (Web Text))

Max Activating Token Index: 170

Text #7

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0469. Min Act: -0.0002

Data Index: 423796 (C4 (Web Text))

Max Activating Token Index: 291

Text #8

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0471. Min Act: -0.0002

Data Index: 464886 (C4 (Web Text))

Max Activating Token Index: 798

Text #9

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0458. Min Act: -0.0002

Data Index: 761249 (C4 (Web Text))

Max Activating Token Index: 390

Text #10

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0487. Min Act: -0.0002

Data Index: 1011420 (C4 (Web Text))

Max Activating Token Index: 928

Text #11

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0460. Min Act: -0.0002

Data Index: 521441 (C4 (Web Text))

Max Activating Token Index: 47

Text #12

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0463. Min Act: -0.0002

Data Index: 401685 (C4 (Web Text))

Max Activating Token Index: 304

Text #13

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0462. Min Act: -0.0002

Data Index: 55956 (C4 (Web Text))

Max Activating Token Index: 235

Text #14

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0460. Min Act: -0.0001

Data Index: 1156270 (C4 (Web Text))

Max Activating Token Index: 284

Text #15

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0459. Min Act: -0.0002

Data Index: 124344 (C4 (Web Text))

Max Activating Token Index: 564

Text #16

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0457. Min Act: -0.0002

Data Index: 1190195 (C4 (Web Text))

Max Activating Token Index: 61

Text #17

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0456. Min Act: -0.0002

Data Index: 359422 (C4 (Web Text))

Max Activating Token Index: 218

Text #18

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0442. Min Act: -0.0001

Data Index: 234582 (C4 (Web Text))

Max Activating Token Index: 359

Text #19

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0453. Min Act: -0.0002

Data Index: 59664 (C4 (Web Text))

Max Activating Token Index: 200