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

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

Neuron 1839 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.1582. Min Range: -6.1582

Max Act: 5.8811. Min Act: -0.0001

Data Index: 646129 (C4 (Web Text))

Max Activating Token Index: 739

Text #1

Max Range: 6.1582. Min Range: -6.1582

Max Act: 6.1582. Min Act: -0.0001

Data Index: 801647 (C4 (Web Text))

Max Activating Token Index: 488

Text #2

Max Range: 6.1582. Min Range: -6.1582

Max Act: 5.6679. Min Act: -0.0001

Data Index: 1138114 (C4 (Web Text))

Max Activating Token Index: 515

Text #3

Max Range: 6.1582. Min Range: -6.1582

Max Act: 5.4996. Min Act: -0.0001

Data Index: 1089192 (C4 (Web Text))

Max Activating Token Index: 526

Text #4

Max Range: 6.1582. Min Range: -6.1582

Max Act: 3.7258. Min Act: -0.0001

Data Index: 615381 (C4 (Web Text))

Max Activating Token Index: 376

Text #5

Max Range: 6.1582. Min Range: -6.1582

Max Act: 3.7907. Min Act: -0.0001

Data Index: 642298 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 6.1582. Min Range: -6.1582

Max Act: 3.8097. Min Act: -0.0001

Data Index: 817867 (C4 (Web Text))

Max Activating Token Index: 943

Text #7

Max Range: 6.1582. Min Range: -6.1582

Max Act: 3.7757. Min Act: -0.0001

Data Index: 801472 (C4 (Web Text))

Max Activating Token Index: 727

Text #8

Max Range: 6.1582. Min Range: -6.1582

Max Act: 3.7831. Min Act: -0.0001

Data Index: 1087418 (C4 (Web Text))

Max Activating Token Index: 323

Text #9

Max Range: 6.1582. Min Range: -6.1582

Max Act: 3.8993. Min Act: -0.0001

Data Index: 1079212 (C4 (Web Text))

Max Activating Token Index: 66

Text #10

Max Range: 6.1582. Min Range: -6.1582

Max Act: 3.3032. Min Act: -0.0001

Data Index: 1119484 (C4 (Web Text))

Max Activating Token Index: 256

Text #11

Max Range: 6.1582. Min Range: -6.1582

Max Act: 3.4923. Min Act: -0.0001

Data Index: 202213 (C4 (Web Text))

Max Activating Token Index: 248

Text #12

Max Range: 6.1582. Min Range: -6.1582

Max Act: 3.3538. Min Act: -0.0001

Data Index: 574356 (C4 (Web Text))

Max Activating Token Index: 268

Text #13

Max Range: 6.1582. Min Range: -6.1582

Max Act: 3.6259. Min Act: -0.0001

Data Index: 1132292 (C4 (Web Text))

Max Activating Token Index: 184

Text #14

Max Range: 6.1582. Min Range: -6.1582

Max Act: 3.4318. Min Act: -0.0001

Data Index: 168743 (C4 (Web Text))

Max Activating Token Index: 649

Text #15

Max Range: 6.1582. Min Range: -6.1582

Max Act: 3.6098. Min Act: -0.0001

Data Index: 1349088 (C4 (Web Text))

Max Activating Token Index: 301

Text #16

Max Range: 6.1582. Min Range: -6.1582

Max Act: 3.3780. Min Act: -0.0001

Data Index: 425069 (C4 (Web Text))

Max Activating Token Index: 627

Text #17

Max Range: 6.1582. Min Range: -6.1582

Max Act: 3.6660. Min Act: -0.0001

Data Index: 713756 (C4 (Web Text))

Max Activating Token Index: 609

Text #18

Max Range: 6.1582. Min Range: -6.1582

Max Act: 3.2206. Min Act: -0.0001

Data Index: 697705 (C4 (Web Text))

Max Activating Token Index: 350

Text #19

Max Range: 6.1582. Min Range: -6.1582

Max Act: 3.5034. Min Act: -0.0001

Data Index: 929248 (C4 (Web Text))

Max Activating Token Index: 596