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

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

Neuron 886 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0527. Min Act: -0.0006

Data Index: 980022 (C4 (Web Text))

Max Activating Token Index: 984

Text #1

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0527. Min Act: -0.0006

Data Index: 731178 (C4 (Web Text))

Max Activating Token Index: 418

Text #2

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0508. Min Act: -0.0006

Data Index: 1171843 (C4 (Web Text))

Max Activating Token Index: 261

Text #3

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0484. Min Act: -0.0005

Data Index: 198341 (C4 (Web Text))

Max Activating Token Index: 347

Text #4

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0470. Min Act: -0.0005

Data Index: 668771 (C4 (Web Text))

Max Activating Token Index: 298

Text #5

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0479. Min Act: -0.0006

Data Index: 181029 (C4 (Web Text))

Max Activating Token Index: 444

Text #6

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0452. Min Act: -0.0006

Data Index: 61453 (C4 (Web Text))

Max Activating Token Index: 868

Text #7

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0478. Min Act: -0.0006

Data Index: 1338467 (C4 (Web Text))

Max Activating Token Index: 943

Text #8

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0448. Min Act: -0.0006

Data Index: 1065406 (C4 (Web Text))

Max Activating Token Index: 320

Text #9

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0438. Min Act: -0.0006

Data Index: 626660 (C4 (Web Text))

Max Activating Token Index: 807

Text #10

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0464. Min Act: -0.0006

Data Index: 836778 (C4 (Web Text))

Max Activating Token Index: 56

Text #11

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0479. Min Act: -0.0006

Data Index: 447301 (C4 (Web Text))

Max Activating Token Index: 923

Text #12

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0452. Min Act: -0.0006

Data Index: 1165105 (C4 (Web Text))

Max Activating Token Index: 126

Text #13

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0450. Min Act: -0.0006

Data Index: 335064 (C4 (Web Text))

Max Activating Token Index: 207

Text #14

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0448. Min Act: -0.0006

Data Index: 1045651 (C4 (Web Text))

Max Activating Token Index: 261

Text #15

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0419. Min Act: -0.0006

Data Index: 303241 (C4 (Web Text))

Max Activating Token Index: 279

Text #16

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0444. Min Act: -0.0006

Data Index: 564782 (C4 (Web Text))

Max Activating Token Index: 114

Text #17

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0453. Min Act: -0.0006

Data Index: 592965 (C4 (Web Text))

Max Activating Token Index: 332

Text #18

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0451. Min Act: -0.0006

Data Index: 370252 (C4 (Web Text))

Max Activating Token Index: 431

Text #19

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0431. Min Act: -0.0006

Data Index: 882985 (C4 (Web Text))

Max Activating Token Index: 944