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

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

Neuron 1250 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8382. Min Range: -1.8382

Max Act: 1.8382. Min Act: -0.0001

Data Index: 790752 (C4 (Web Text))

Max Activating Token Index: 516

Text #1

Max Range: 1.8382. Min Range: -1.8382

Max Act: 1.1463. Min Act: -0.0001

Data Index: 837244 (C4 (Web Text))

Max Activating Token Index: 738

Text #2

Max Range: 1.8382. Min Range: -1.8382

Max Act: 1.0801. Min Act: -0.0001

Data Index: 693985 (C4 (Web Text))

Max Activating Token Index: 296

Text #3

Max Range: 1.8382. Min Range: -1.8382

Max Act: 1.3769. Min Act: -0.0002

Data Index: 80373 (C4 (Web Text))

Max Activating Token Index: 571

Text #4

Max Range: 1.8382. Min Range: -1.8382

Max Act: 1.1847. Min Act: -0.0002

Data Index: 435532 (C4 (Web Text))

Max Activating Token Index: 910

Text #5

Max Range: 1.8382. Min Range: -1.8382

Max Act: 1.1185. Min Act: -0.0001

Data Index: 370379 (C4 (Web Text))

Max Activating Token Index: 179

Text #6

Max Range: 1.8382. Min Range: -1.8382

Max Act: 1.1887. Min Act: -0.0001

Data Index: 64664 (C4 (Web Text))

Max Activating Token Index: 817

Text #7

Max Range: 1.8382. Min Range: -1.8382

Max Act: 1.0038. Min Act: -0.0001

Data Index: 52262 (C4 (Web Text))

Max Activating Token Index: 433

Text #8

Max Range: 1.8382. Min Range: -1.8382

Max Act: 1.1628. Min Act: -0.0001

Data Index: 643249 (C4 (Web Text))

Max Activating Token Index: 248

Text #9

Max Range: 1.8382. Min Range: -1.8382

Max Act: 1.0639. Min Act: -0.0001

Data Index: 1077166 (C4 (Web Text))

Max Activating Token Index: 525

Text #10

Max Range: 1.8382. Min Range: -1.8382

Max Act: 0.8856. Min Act: -0.0001

Data Index: 92025 (C4 (Web Text))

Max Activating Token Index: 824

Text #11

Max Range: 1.8382. Min Range: -1.8382

Max Act: 1.0305. Min Act: -0.0001

Data Index: 864042 (C4 (Web Text))

Max Activating Token Index: 313

Text #12

Max Range: 1.8382. Min Range: -1.8382

Max Act: 0.9918. Min Act: -0.0001

Data Index: 1338037 (C4 (Web Text))

Max Activating Token Index: 76

Text #13

Max Range: 1.8382. Min Range: -1.8382

Max Act: 1.0527. Min Act: -0.0001

Data Index: 830142 (C4 (Web Text))

Max Activating Token Index: 464

Text #14

Max Range: 1.8382. Min Range: -1.8382

Max Act: 0.9043. Min Act: -0.0001

Data Index: 1152571 (C4 (Web Text))

Max Activating Token Index: 447

Text #15

Max Range: 1.8382. Min Range: -1.8382

Max Act: 0.9768. Min Act: -0.0001

Data Index: 105071 (C4 (Web Text))

Max Activating Token Index: 185

Text #16

Max Range: 1.8382. Min Range: -1.8382

Max Act: 1.0023. Min Act: -0.0001

Data Index: 578924 (C4 (Web Text))

Max Activating Token Index: 267

Text #17

Max Range: 1.8382. Min Range: -1.8382

Max Act: 1.0843. Min Act: -0.0001

Data Index: 1329281 (C4 (Web Text))

Max Activating Token Index: 471

Text #18

Max Range: 1.8382. Min Range: -1.8382

Max Act: 1.1322. Min Act: -0.0001

Data Index: 466274 (C4 (Web Text))

Max Activating Token Index: 133

Text #19

Max Range: 1.8382. Min Range: -1.8382

Max Act: 1.0330. Min Act: -0.0001

Data Index: 191043 (C4 (Web Text))

Max Activating Token Index: 583