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

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

Neuron 4117 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0942. Min Act: -0.0003

Data Index: 421706 (C4 (Web Text))

Max Activating Token Index: 829

Text #1

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0802. Min Act: -0.0003

Data Index: 1335078 (C4 (Web Text))

Max Activating Token Index: 697

Text #2

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0798. Min Act: -0.0003

Data Index: 694831 (C4 (Web Text))

Max Activating Token Index: 226

Text #3

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0793. Min Act: -0.0003

Data Index: 929983 (C4 (Web Text))

Max Activating Token Index: 261

Text #4

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0741. Min Act: -0.0003

Data Index: 1260172 (C4 (Web Text))

Max Activating Token Index: 299

Text #5

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0741. Min Act: -0.0003

Data Index: 1161093 (C4 (Web Text))

Max Activating Token Index: 645

Text #6

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0726. Min Act: -0.0003

Data Index: 1075241 (C4 (Web Text))

Max Activating Token Index: 263

Text #7

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0717. Min Act: -0.0003

Data Index: 48648 (C4 (Web Text))

Max Activating Token Index: 475

Text #8

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0711. Min Act: -0.0003

Data Index: 1092356 (C4 (Web Text))

Max Activating Token Index: 499

Text #9

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0708. Min Act: -0.0003

Data Index: 693638 (C4 (Web Text))

Max Activating Token Index: 147

Text #10

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0682. Min Act: -0.0003

Data Index: 95752 (C4 (Web Text))

Max Activating Token Index: 628

Text #11

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0702. Min Act: -0.0003

Data Index: 1187088 (C4 (Web Text))

Max Activating Token Index: 294

Text #12

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0675. Min Act: -0.0003

Data Index: 672368 (C4 (Web Text))

Max Activating Token Index: 715

Text #13

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0695. Min Act: -0.0003

Data Index: 462267 (C4 (Web Text))

Max Activating Token Index: 69

Text #14

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0691. Min Act: -0.0003

Data Index: 898156 (C4 (Web Text))

Max Activating Token Index: 226

Text #15

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0720. Min Act: -0.0003

Data Index: 601306 (C4 (Web Text))

Max Activating Token Index: 592

Text #16

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0693. Min Act: -0.0003

Data Index: 307453 (C4 (Web Text))

Max Activating Token Index: 462

Text #17

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0664. Min Act: -0.0002

Data Index: 419053 (C4 (Web Text))

Max Activating Token Index: 464

Text #18

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0658. Min Act: -0.0003

Data Index: 1200910 (C4 (Web Text))

Max Activating Token Index: 161

Text #19

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0682. Min Act: -0.0003

Data Index: 1148880 (C4 (Web Text))

Max Activating Token Index: 148