Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2292 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0628. Min Act: -0.0002

Data Index: 197440 (C4 (Web Text))

Max Activating Token Index: 175

Text #1

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0596. Min Act: -0.0002

Data Index: 586536 (C4 (Web Text))

Max Activating Token Index: 151

Text #2

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0552. Min Act: -0.0002

Data Index: 700701 (C4 (Web Text))

Max Activating Token Index: 175

Text #3

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0536. Min Act: -0.0002

Data Index: 130994 (C4 (Web Text))

Max Activating Token Index: 144

Text #4

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0498. Min Act: -0.0002

Data Index: 141233 (C4 (Web Text))

Max Activating Token Index: 62

Text #5

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0479. Min Act: -0.0002

Data Index: 1143989 (C4 (Web Text))

Max Activating Token Index: 274

Text #6

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0469. Min Act: -0.0002

Data Index: 1033021 (C4 (Web Text))

Max Activating Token Index: 963

Text #7

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0426. Min Act: -0.0002

Data Index: 11281 (C4 (Web Text))

Max Activating Token Index: 307

Text #8

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0416. Min Act: -0.0002

Data Index: 321451 (C4 (Web Text))

Max Activating Token Index: 153

Text #9

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0412. Min Act: -0.0002

Data Index: 97351 (C4 (Web Text))

Max Activating Token Index: 150

Text #10

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0410. Min Act: -0.0002

Data Index: 817174 (C4 (Web Text))

Max Activating Token Index: 226

Text #11

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0402. Min Act: -0.0001

Data Index: 1294899 (C4 (Web Text))

Max Activating Token Index: 195

Text #12

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0408. Min Act: -0.0002

Data Index: 1009875 (C4 (Web Text))

Max Activating Token Index: 360

Text #13

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0392. Min Act: -0.0002

Data Index: 1288025 (C4 (Web Text))

Max Activating Token Index: 183

Text #14

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0395. Min Act: -0.0002

Data Index: 4421 (C4 (Web Text))

Max Activating Token Index: 545

Text #15

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0398. Min Act: -0.0002

Data Index: 24900 (C4 (Web Text))

Max Activating Token Index: 77

Text #16

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0385. Min Act: -0.0001

Data Index: 1085892 (C4 (Web Text))

Max Activating Token Index: 336

Text #17

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0383. Min Act: -0.0001

Data Index: 241337 (C4 (Web Text))

Max Activating Token Index: 199

Text #18

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0382. Min Act: -0.0001

Data Index: 1067206 (C4 (Web Text))

Max Activating Token Index: 244

Text #19

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0370. Min Act: -0.0001

Data Index: 369912 (C4 (Web Text))

Max Activating Token Index: 88