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

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

Neuron 4220 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6221. Min Range: -3.6221

Max Act: 3.6221. Min Act: -0.0000

Data Index: 856261 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 3.6221. Min Range: -3.6221

Max Act: 3.4373. Min Act: -0.0000

Data Index: 127703 (C4 (Web Text))

Max Activating Token Index: 684

Text #2

Max Range: 3.6221. Min Range: -3.6221

Max Act: 3.1928. Min Act: -0.0000

Data Index: 1215956 (C4 (Web Text))

Max Activating Token Index: 201

Text #3

Max Range: 3.6221. Min Range: -3.6221

Max Act: 2.4032. Min Act: -0.0001

Data Index: 667459 (C4 (Web Text))

Max Activating Token Index: 992

Text #4

Max Range: 3.6221. Min Range: -3.6221

Max Act: 2.8785. Min Act: -0.0000

Data Index: 58302 (C4 (Web Text))

Max Activating Token Index: 580

Text #5

Max Range: 3.6221. Min Range: -3.6221

Max Act: 3.2836. Min Act: -0.0000

Data Index: 134015 (C4 (Web Text))

Max Activating Token Index: 253

Text #6

Max Range: 3.6221. Min Range: -3.6221

Max Act: 2.9541. Min Act: -0.0000

Data Index: 156120 (C4 (Web Text))

Max Activating Token Index: 31

Text #7

Max Range: 3.6221. Min Range: -3.6221

Max Act: 2.6682. Min Act: -0.0000

Data Index: 547428 (C4 (Web Text))

Max Activating Token Index: 378

Text #8

Max Range: 3.6221. Min Range: -3.6221

Max Act: 2.9214. Min Act: -0.0000

Data Index: 21791 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 3.6221. Min Range: -3.6221

Max Act: 2.9087. Min Act: -0.0000

Data Index: 61300 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 3.6221. Min Range: -3.6221

Max Act: 2.7498. Min Act: -0.0000

Data Index: 666593 (C4 (Web Text))

Max Activating Token Index: 792

Text #11

Max Range: 3.6221. Min Range: -3.6221

Max Act: 2.6888. Min Act: -0.0000

Data Index: 12360 (C4 (Web Text))

Max Activating Token Index: 222

Text #12

Max Range: 3.6221. Min Range: -3.6221

Max Act: 2.9416. Min Act: -0.0000

Data Index: 366882 (C4 (Web Text))

Max Activating Token Index: 853

Text #13

Max Range: 3.6221. Min Range: -3.6221

Max Act: 2.6450. Min Act: -0.0000

Data Index: 601998 (C4 (Web Text))

Max Activating Token Index: 322

Text #14

Max Range: 3.6221. Min Range: -3.6221

Max Act: 2.7188. Min Act: -0.0000

Data Index: 460093 (C4 (Web Text))

Max Activating Token Index: 154

Text #15

Max Range: 3.6221. Min Range: -3.6221

Max Act: 2.4748. Min Act: -0.0000

Data Index: 356678 (C4 (Web Text))

Max Activating Token Index: 6

Text #16

Max Range: 3.6221. Min Range: -3.6221

Max Act: 2.5211. Min Act: -0.0000

Data Index: 1068670 (C4 (Web Text))

Max Activating Token Index: 985

Text #17

Max Range: 3.6221. Min Range: -3.6221

Max Act: 2.7616. Min Act: -0.0000

Data Index: 1129079 (C4 (Web Text))

Max Activating Token Index: 313

Text #18

Max Range: 3.6221. Min Range: -3.6221

Max Act: 2.4918. Min Act: -0.0000

Data Index: 119616 (C4 (Web Text))

Max Activating Token Index: 319

Text #19

Max Range: 3.6221. Min Range: -3.6221

Max Act: 2.6173. Min Act: -0.0000

Data Index: 1197030 (C4 (Web Text))

Max Activating Token Index: 71