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

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

Neuron 3449 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9078. Min Range: -1.9078

Max Act: 1.8693. Min Act: -0.0001

Data Index: 753224 (C4 (Web Text))

Max Activating Token Index: 85

Text #1

Max Range: 1.9078. Min Range: -1.9078

Max Act: 1.7863. Min Act: -0.0001

Data Index: 364532 (C4 (Web Text))

Max Activating Token Index: 228

Text #2

Max Range: 1.9078. Min Range: -1.9078

Max Act: 1.7348. Min Act: -0.0001

Data Index: 818301 (C4 (Web Text))

Max Activating Token Index: 189

Text #3

Max Range: 1.9078. Min Range: -1.9078

Max Act: 1.8255. Min Act: -0.0001

Data Index: 1334797 (C4 (Web Text))

Max Activating Token Index: 87

Text #4

Max Range: 1.9078. Min Range: -1.9078

Max Act: 1.9078. Min Act: -0.0001

Data Index: 41071 (C4 (Web Text))

Max Activating Token Index: 432

Text #5

Max Range: 1.9078. Min Range: -1.9078

Max Act: 1.7758. Min Act: -0.0001

Data Index: 1030695 (C4 (Web Text))

Max Activating Token Index: 488

Text #6

Max Range: 1.9078. Min Range: -1.9078

Max Act: 1.7201. Min Act: -0.0001

Data Index: 26061 (C4 (Web Text))

Max Activating Token Index: 150

Text #7

Max Range: 1.9078. Min Range: -1.9078

Max Act: 1.6684. Min Act: -0.0001

Data Index: 107116 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 1.9078. Min Range: -1.9078

Max Act: 1.6092. Min Act: -0.0001

Data Index: 1344053 (C4 (Web Text))

Max Activating Token Index: 199

Text #9

Max Range: 1.9078. Min Range: -1.9078

Max Act: 1.8211. Min Act: -0.0001

Data Index: 1009960 (C4 (Web Text))

Max Activating Token Index: 393

Text #10

Max Range: 1.9078. Min Range: -1.9078

Max Act: 1.7237. Min Act: -0.0001

Data Index: 124898 (C4 (Web Text))

Max Activating Token Index: 380

Text #11

Max Range: 1.9078. Min Range: -1.9078

Max Act: 1.6488. Min Act: -0.0001

Data Index: 637589 (C4 (Web Text))

Max Activating Token Index: 521

Text #12

Max Range: 1.9078. Min Range: -1.9078

Max Act: 1.5695. Min Act: -0.0001

Data Index: 256511 (C4 (Web Text))

Max Activating Token Index: 222

Text #13

Max Range: 1.9078. Min Range: -1.9078

Max Act: 1.5360. Min Act: -0.0001

Data Index: 282585 (C4 (Web Text))

Max Activating Token Index: 362

Text #14

Max Range: 1.9078. Min Range: -1.9078

Max Act: 1.5246. Min Act: -0.0001

Data Index: 1097393 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 1.9078. Min Range: -1.9078

Max Act: 1.6182. Min Act: -0.0001

Data Index: 800283 (C4 (Web Text))

Max Activating Token Index: 453

Text #16

Max Range: 1.9078. Min Range: -1.9078

Max Act: 1.4060. Min Act: -0.0001

Data Index: 526317 (C4 (Web Text))

Max Activating Token Index: 245

Text #17

Max Range: 1.9078. Min Range: -1.9078

Max Act: 1.5919. Min Act: -0.0001

Data Index: 522330 (C4 (Web Text))

Max Activating Token Index: 566

Text #18

Max Range: 1.9078. Min Range: -1.9078

Max Act: 1.4826. Min Act: -0.0001

Data Index: 34987 (C4 (Web Text))

Max Activating Token Index: 158

Text #19

Max Range: 1.9078. Min Range: -1.9078

Max Act: 1.5268. Min Act: -0.0001

Data Index: 361684 (C4 (Web Text))

Max Activating Token Index: 97