Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1936 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2596. Min Act: -0.0001

Data Index: 28495 (C4 (Web Text))

Max Activating Token Index: 508

Text #1

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2261. Min Act: -0.0001

Data Index: 195606 (C4 (Web Text))

Max Activating Token Index: 880

Text #2

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2410. Min Act: -0.0001

Data Index: 87374 (C4 (Web Text))

Max Activating Token Index: 751

Text #3

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2645. Min Act: -0.0001

Data Index: 266221 (C4 (Web Text))

Max Activating Token Index: 777

Text #4

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2675. Min Act: -0.0001

Data Index: 1184726 (C4 (Web Text))

Max Activating Token Index: 904

Text #5

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2388. Min Act: -0.0001

Data Index: 104426 (C4 (Web Text))

Max Activating Token Index: 538

Text #6

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2089. Min Act: -0.0001

Data Index: 502128 (C4 (Web Text))

Max Activating Token Index: 821

Text #7

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2300. Min Act: -0.0001

Data Index: 919540 (C4 (Web Text))

Max Activating Token Index: 659

Text #8

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2188. Min Act: -0.0001

Data Index: 775186 (C4 (Web Text))

Max Activating Token Index: 765

Text #9

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2271. Min Act: -0.0001

Data Index: 1144669 (C4 (Web Text))

Max Activating Token Index: 248

Text #10

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2332. Min Act: -0.0001

Data Index: 311161 (C4 (Web Text))

Max Activating Token Index: 983

Text #11

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2234. Min Act: -0.0001

Data Index: 1073478 (C4 (Web Text))

Max Activating Token Index: 132

Text #12

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2162. Min Act: -0.0001

Data Index: 431667 (C4 (Web Text))

Max Activating Token Index: 285

Text #13

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2063. Min Act: -0.0001

Data Index: 1322966 (C4 (Web Text))

Max Activating Token Index: 845

Text #14

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2110. Min Act: -0.0001

Data Index: 945952 (C4 (Web Text))

Max Activating Token Index: 543

Text #15

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2169. Min Act: -0.0001

Data Index: 996143 (C4 (Web Text))

Max Activating Token Index: 254

Text #16

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2036. Min Act: -0.0001

Data Index: 1256881 (C4 (Web Text))

Max Activating Token Index: 19

Text #17

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2110. Min Act: -0.0001

Data Index: 1004581 (C4 (Web Text))

Max Activating Token Index: 138

Text #18

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2164. Min Act: -0.0001

Data Index: 1023751 (C4 (Web Text))

Max Activating Token Index: 131

Text #19

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2245. Min Act: -0.0001

Data Index: 412355 (C4 (Web Text))

Max Activating Token Index: 47