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

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

Neuron 1107 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: 0.4170. Min Range: -0.4170

Max Act: 0.4170. Min Act: 0.0000

Data Index: 422726 (C4 (Web Text))

Max Activating Token Index: 109

Text #1

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.4044. Min Act: -0.0000

Data Index: 1538866 (Python Code)

Max Activating Token Index: 178

Text #2

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.3971. Min Act: -0.0000

Data Index: 1363597 (Python Code)

Max Activating Token Index: 287

Text #3

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.3470. Min Act: -0.0000

Data Index: 830344 (C4 (Web Text))

Max Activating Token Index: 895

Text #4

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.3466. Min Act: -0.0000

Data Index: 10484 (C4 (Web Text))

Max Activating Token Index: 319

Text #5

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.3412. Min Act: -0.0000

Data Index: 1269415 (C4 (Web Text))

Max Activating Token Index: 552

Text #6

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.3413. Min Act: 0.0000

Data Index: 290688 (C4 (Web Text))

Max Activating Token Index: 425

Text #7

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.3495. Min Act: -0.0000

Data Index: 133578 (C4 (Web Text))

Max Activating Token Index: 733

Text #8

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.2860. Min Act: -0.0000

Data Index: 1362302 (Python Code)

Max Activating Token Index: 185

Text #9

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.2801. Min Act: -0.0000

Data Index: 1553348 (Python Code)

Max Activating Token Index: 92

Text #10

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.3212. Min Act: -0.0000

Data Index: 870062 (C4 (Web Text))

Max Activating Token Index: 744

Text #11

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.3051. Min Act: -0.0000

Data Index: 1636234 (Python Code)

Max Activating Token Index: 157

Text #12

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.3062. Min Act: -0.0000

Data Index: 363884 (C4 (Web Text))

Max Activating Token Index: 460

Text #13

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.3051. Min Act: 0.0000

Data Index: 1296192 (C4 (Web Text))

Max Activating Token Index: 330

Text #14

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.3228. Min Act: 0.0000

Data Index: 1335101 (C4 (Web Text))

Max Activating Token Index: 99

Text #15

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.2960. Min Act: -0.0000

Data Index: 729163 (C4 (Web Text))

Max Activating Token Index: 1014

Text #16

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.2912. Min Act: -0.0000

Data Index: 509089 (C4 (Web Text))

Max Activating Token Index: 758

Text #17

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.2908. Min Act: -0.0000

Data Index: 1312197 (C4 (Web Text))

Max Activating Token Index: 356

Text #18

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.2809. Min Act: -0.0000

Data Index: 1268093 (C4 (Web Text))

Max Activating Token Index: 802

Text #19

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.2893. Min Act: 0.0000

Data Index: 117449 (C4 (Web Text))

Max Activating Token Index: 548