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

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

Neuron 2824 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4724. Min Range: -1.4724

Max Act: 1.4724. Min Act: -0.0001

Data Index: 1168798 (C4 (Web Text))

Max Activating Token Index: 77

Text #1

Max Range: 1.4724. Min Range: -1.4724

Max Act: 1.2906. Min Act: -0.0001

Data Index: 30051 (C4 (Web Text))

Max Activating Token Index: 604

Text #2

Max Range: 1.4724. Min Range: -1.4724

Max Act: 1.2767. Min Act: -0.0001

Data Index: 179488 (C4 (Web Text))

Max Activating Token Index: 823

Text #3

Max Range: 1.4724. Min Range: -1.4724

Max Act: 1.2141. Min Act: -0.0001

Data Index: 1001039 (C4 (Web Text))

Max Activating Token Index: 739

Text #4

Max Range: 1.4724. Min Range: -1.4724

Max Act: 1.2161. Min Act: -0.0001

Data Index: 975314 (C4 (Web Text))

Max Activating Token Index: 387

Text #5

Max Range: 1.4724. Min Range: -1.4724

Max Act: 1.3086. Min Act: -0.0001

Data Index: 368556 (C4 (Web Text))

Max Activating Token Index: 526

Text #6

Max Range: 1.4724. Min Range: -1.4724

Max Act: 1.3056. Min Act: -0.0001

Data Index: 420706 (C4 (Web Text))

Max Activating Token Index: 890

Text #7

Max Range: 1.4724. Min Range: -1.4724

Max Act: 1.2252. Min Act: -0.0001

Data Index: 789752 (C4 (Web Text))

Max Activating Token Index: 324

Text #8

Max Range: 1.4724. Min Range: -1.4724

Max Act: 1.2848. Min Act: -0.0001

Data Index: 635168 (C4 (Web Text))

Max Activating Token Index: 3

Text #9

Max Range: 1.4724. Min Range: -1.4724

Max Act: 1.2355. Min Act: -0.0001

Data Index: 804471 (C4 (Web Text))

Max Activating Token Index: 735

Text #10

Max Range: 1.4724. Min Range: -1.4724

Max Act: 1.2396. Min Act: -0.0001

Data Index: 864922 (C4 (Web Text))

Max Activating Token Index: 708

Text #11

Max Range: 1.4724. Min Range: -1.4724

Max Act: 1.2063. Min Act: -0.0001

Data Index: 65145 (C4 (Web Text))

Max Activating Token Index: 107

Text #12

Max Range: 1.4724. Min Range: -1.4724

Max Act: 1.1711. Min Act: -0.0001

Data Index: 1121842 (C4 (Web Text))

Max Activating Token Index: 432

Text #13

Max Range: 1.4724. Min Range: -1.4724

Max Act: 1.1289. Min Act: -0.0001

Data Index: 121811 (C4 (Web Text))

Max Activating Token Index: 595

Text #14

Max Range: 1.4724. Min Range: -1.4724

Max Act: 1.1194. Min Act: -0.0001

Data Index: 1302550 (C4 (Web Text))

Max Activating Token Index: 699

Text #15

Max Range: 1.4724. Min Range: -1.4724

Max Act: 1.0863. Min Act: -0.0001

Data Index: 22160 (C4 (Web Text))

Max Activating Token Index: 238

Text #16

Max Range: 1.4724. Min Range: -1.4724

Max Act: 1.1295. Min Act: -0.0000

Data Index: 1398370 (Python Code)

Max Activating Token Index: 277

Text #17

Max Range: 1.4724. Min Range: -1.4724

Max Act: 1.1079. Min Act: -0.0001

Data Index: 1034244 (C4 (Web Text))

Max Activating Token Index: 110

Text #18

Max Range: 1.4724. Min Range: -1.4724

Max Act: 1.1338. Min Act: -0.0000

Data Index: 859174 (C4 (Web Text))

Max Activating Token Index: 734

Text #19

Max Range: 1.4724. Min Range: -1.4724

Max Act: 1.1848. Min Act: -0.0001

Data Index: 950615 (C4 (Web Text))

Max Activating Token Index: 37