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

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

Neuron 4877 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5322. Min Range: -2.5322

Max Act: 2.5322. Min Act: -0.0000

Data Index: 1121284 (C4 (Web Text))

Max Activating Token Index: 987

Text #1

Max Range: 2.5322. Min Range: -2.5322

Max Act: 1.9860. Min Act: -0.0000

Data Index: 749012 (C4 (Web Text))

Max Activating Token Index: 286

Text #2

Max Range: 2.5322. Min Range: -2.5322

Max Act: 2.0232. Min Act: -0.0000

Data Index: 260446 (C4 (Web Text))

Max Activating Token Index: 179

Text #3

Max Range: 2.5322. Min Range: -2.5322

Max Act: 1.9645. Min Act: -0.0000

Data Index: 933286 (C4 (Web Text))

Max Activating Token Index: 76

Text #4

Max Range: 2.5322. Min Range: -2.5322

Max Act: 1.9342. Min Act: -0.0000

Data Index: 374201 (C4 (Web Text))

Max Activating Token Index: 127

Text #5

Max Range: 2.5322. Min Range: -2.5322

Max Act: 1.6913. Min Act: -0.0000

Data Index: 39719 (C4 (Web Text))

Max Activating Token Index: 631

Text #6

Max Range: 2.5322. Min Range: -2.5322

Max Act: 1.9162. Min Act: -0.0000

Data Index: 1071401 (C4 (Web Text))

Max Activating Token Index: 284

Text #7

Max Range: 2.5322. Min Range: -2.5322

Max Act: 1.6096. Min Act: -0.0000

Data Index: 1320432 (C4 (Web Text))

Max Activating Token Index: 72

Text #8

Max Range: 2.5322. Min Range: -2.5322

Max Act: 1.6250. Min Act: -0.0000

Data Index: 959261 (C4 (Web Text))

Max Activating Token Index: 711

Text #9

Max Range: 2.5322. Min Range: -2.5322

Max Act: 1.6989. Min Act: -0.0000

Data Index: 765549 (C4 (Web Text))

Max Activating Token Index: 227

Text #10

Max Range: 2.5322. Min Range: -2.5322

Max Act: 1.4772. Min Act: -0.0000

Data Index: 563565 (C4 (Web Text))

Max Activating Token Index: 47

Text #11

Max Range: 2.5322. Min Range: -2.5322

Max Act: 1.5022. Min Act: -0.0000

Data Index: 167296 (C4 (Web Text))

Max Activating Token Index: 888

Text #12

Max Range: 2.5322. Min Range: -2.5322

Max Act: 1.4763. Min Act: -0.0000

Data Index: 1129460 (C4 (Web Text))

Max Activating Token Index: 227

Text #13

Max Range: 2.5322. Min Range: -2.5322

Max Act: 1.4672. Min Act: -0.0000

Data Index: 892036 (C4 (Web Text))

Max Activating Token Index: 467

Text #14

Max Range: 2.5322. Min Range: -2.5322

Max Act: 1.3597. Min Act: -0.0000

Data Index: 542129 (C4 (Web Text))

Max Activating Token Index: 318

Text #15

Max Range: 2.5322. Min Range: -2.5322

Max Act: 1.4202. Min Act: -0.0000

Data Index: 1040265 (C4 (Web Text))

Max Activating Token Index: 950

Text #16

Max Range: 2.5322. Min Range: -2.5322

Max Act: 1.4149. Min Act: -0.0000

Data Index: 1163832 (C4 (Web Text))

Max Activating Token Index: 946

Text #17

Max Range: 2.5322. Min Range: -2.5322

Max Act: 1.5027. Min Act: -0.0000

Data Index: 414906 (C4 (Web Text))

Max Activating Token Index: 652

Text #18

Max Range: 2.5322. Min Range: -2.5322

Max Act: 1.2570. Min Act: -0.0000

Data Index: 592706 (C4 (Web Text))

Max Activating Token Index: 865

Text #19

Max Range: 2.5322. Min Range: -2.5322

Max Act: 1.2482. Min Act: -0.0000

Data Index: 62525 (C4 (Web Text))

Max Activating Token Index: 378