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

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

Neuron 1117 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8439. Min Range: -1.8439

Max Act: 1.8439. Min Act: 0.0000

Data Index: 1095947 (C4 (Web Text))

Max Activating Token Index: 393

Text #1

Max Range: 1.8439. Min Range: -1.8439

Max Act: 1.7190. Min Act: -0.0000

Data Index: 949369 (C4 (Web Text))

Max Activating Token Index: 974

Text #2

Max Range: 1.8439. Min Range: -1.8439

Max Act: 1.4673. Min Act: 0.0000

Data Index: 1305419 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 1.8439. Min Range: -1.8439

Max Act: 1.5007. Min Act: 0.0001

Data Index: 406372 (C4 (Web Text))

Max Activating Token Index: 630

Text #4

Max Range: 1.8439. Min Range: -1.8439

Max Act: 1.3693. Min Act: -0.0000

Data Index: 1096049 (C4 (Web Text))

Max Activating Token Index: 461

Text #5

Max Range: 1.8439. Min Range: -1.8439

Max Act: 1.3369. Min Act: -0.0000

Data Index: 310946 (C4 (Web Text))

Max Activating Token Index: 641

Text #6

Max Range: 1.8439. Min Range: -1.8439

Max Act: 1.4040. Min Act: -0.0000

Data Index: 1064548 (C4 (Web Text))

Max Activating Token Index: 79

Text #7

Max Range: 1.8439. Min Range: -1.8439

Max Act: 1.3576. Min Act: -0.0000

Data Index: 1419434 (Python Code)

Max Activating Token Index: 709

Text #8

Max Range: 1.8439. Min Range: -1.8439

Max Act: 1.2797. Min Act: -0.0000

Data Index: 177923 (C4 (Web Text))

Max Activating Token Index: 304

Text #9

Max Range: 1.8439. Min Range: -1.8439

Max Act: 1.2183. Min Act: -0.0000

Data Index: 1401943 (Python Code)

Max Activating Token Index: 57

Text #10

Max Range: 1.8439. Min Range: -1.8439

Max Act: 1.2863. Min Act: 0.0001

Data Index: 1327801 (C4 (Web Text))

Max Activating Token Index: 693

Text #11

Max Range: 1.8439. Min Range: -1.8439

Max Act: 1.2567. Min Act: -0.0000

Data Index: 617757 (C4 (Web Text))

Max Activating Token Index: 85

Text #12

Max Range: 1.8439. Min Range: -1.8439

Max Act: 1.1824. Min Act: 0.0002

Data Index: 767016 (C4 (Web Text))

Max Activating Token Index: 1004

Text #13

Max Range: 1.8439. Min Range: -1.8439

Max Act: 1.2180. Min Act: -0.0000

Data Index: 266086 (C4 (Web Text))

Max Activating Token Index: 95

Text #14

Max Range: 1.8439. Min Range: -1.8439

Max Act: 1.2095. Min Act: -0.0000

Data Index: 816696 (C4 (Web Text))

Max Activating Token Index: 333

Text #15

Max Range: 1.8439. Min Range: -1.8439

Max Act: 1.1888. Min Act: 0.0001

Data Index: 211251 (C4 (Web Text))

Max Activating Token Index: 38

Text #16

Max Range: 1.8439. Min Range: -1.8439

Max Act: 1.1520. Min Act: -0.0000

Data Index: 409931 (C4 (Web Text))

Max Activating Token Index: 170

Text #17

Max Range: 1.8439. Min Range: -1.8439

Max Act: 1.1344. Min Act: -0.0000

Data Index: 143392 (C4 (Web Text))

Max Activating Token Index: 621

Text #18

Max Range: 1.8439. Min Range: -1.8439

Max Act: 1.0157. Min Act: -0.0000

Data Index: 898276 (C4 (Web Text))

Max Activating Token Index: 243

Text #19

Max Range: 1.8439. Min Range: -1.8439

Max Act: 1.1390. Min Act: -0.0000

Data Index: 816310 (C4 (Web Text))

Max Activating Token Index: 167