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

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

Neuron 1343 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2567. Min Act: -0.0000

Data Index: 1548128 (Python Code)

Max Activating Token Index: 461

Text #1

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1374. Min Act: -0.0000

Data Index: 1595101 (Python Code)

Max Activating Token Index: 381

Text #2

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1315. Min Act: -0.0000

Data Index: 1171310 (C4 (Web Text))

Max Activating Token Index: 503

Text #3

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1326. Min Act: -0.0000

Data Index: 723726 (C4 (Web Text))

Max Activating Token Index: 722

Text #4

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1231. Min Act: -0.0000

Data Index: 611593 (C4 (Web Text))

Max Activating Token Index: 61

Text #5

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1262. Min Act: -0.0000

Data Index: 1513919 (Python Code)

Max Activating Token Index: 685

Text #6

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1235. Min Act: -0.0000

Data Index: 866568 (C4 (Web Text))

Max Activating Token Index: 333

Text #7

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1144. Min Act: -0.0000

Data Index: 1397618 (Python Code)

Max Activating Token Index: 315

Text #8

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1186. Min Act: -0.0000

Data Index: 1586106 (Python Code)

Max Activating Token Index: 193

Text #9

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1129. Min Act: -0.0000

Data Index: 1528016 (Python Code)

Max Activating Token Index: 904

Text #10

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1154. Min Act: -0.0000

Data Index: 1533358 (Python Code)

Max Activating Token Index: 560

Text #11

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1161. Min Act: -0.0000

Data Index: 1304114 (C4 (Web Text))

Max Activating Token Index: 319

Text #12

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1151. Min Act: -0.0000

Data Index: 1229817 (C4 (Web Text))

Max Activating Token Index: 431

Text #13

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1123. Min Act: -0.0000

Data Index: 1383921 (Python Code)

Max Activating Token Index: 797

Text #14

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1076. Min Act: -0.0000

Data Index: 348536 (C4 (Web Text))

Max Activating Token Index: 630

Text #15

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1073. Min Act: -0.0000

Data Index: 1558326 (Python Code)

Max Activating Token Index: 183

Text #16

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1059. Min Act: -0.0000

Data Index: 1522363 (Python Code)

Max Activating Token Index: 603

Text #17

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1010. Min Act: -0.0000

Data Index: 1564752 (Python Code)

Max Activating Token Index: 962

Text #18

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1016. Min Act: -0.0000

Data Index: 1605351 (Python Code)

Max Activating Token Index: 121

Text #19

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1001. Min Act: -0.0000

Data Index: 617219 (C4 (Web Text))

Max Activating Token Index: 852