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

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

Neuron 3038 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: 1.8541. Min Range: -1.8541

Max Act: 1.8541. Min Act: -0.0000

Data Index: 351789 (C4 (Web Text))

Max Activating Token Index: 547

Text #1

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.7798. Min Act: -0.0000

Data Index: 896756 (C4 (Web Text))

Max Activating Token Index: 154

Text #2

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.7610. Min Act: -0.0000

Data Index: 251014 (C4 (Web Text))

Max Activating Token Index: 831

Text #3

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.7339. Min Act: -0.0000

Data Index: 999976 (C4 (Web Text))

Max Activating Token Index: 925

Text #4

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.6506. Min Act: -0.0000

Data Index: 10266 (C4 (Web Text))

Max Activating Token Index: 969

Text #5

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.6400. Min Act: -0.0000

Data Index: 534695 (C4 (Web Text))

Max Activating Token Index: 500

Text #6

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.6210. Min Act: -0.0000

Data Index: 1226040 (C4 (Web Text))

Max Activating Token Index: 947

Text #7

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.5624. Min Act: -0.0000

Data Index: 372371 (C4 (Web Text))

Max Activating Token Index: 607

Text #8

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.5417. Min Act: -0.0000

Data Index: 913847 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.5918. Min Act: -0.0000

Data Index: 540031 (C4 (Web Text))

Max Activating Token Index: 193

Text #10

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.5897. Min Act: -0.0000

Data Index: 1248963 (C4 (Web Text))

Max Activating Token Index: 331

Text #11

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.4956. Min Act: -0.0000

Data Index: 512731 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.3845. Min Act: -0.0000

Data Index: 416306 (C4 (Web Text))

Max Activating Token Index: 1005

Text #13

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.4443. Min Act: -0.0000

Data Index: 1296027 (C4 (Web Text))

Max Activating Token Index: 970

Text #14

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.4940. Min Act: -0.0000

Data Index: 873550 (C4 (Web Text))

Max Activating Token Index: 153

Text #15

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.4120. Min Act: -0.0000

Data Index: 267598 (C4 (Web Text))

Max Activating Token Index: 1001

Text #16

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.4104. Min Act: -0.0000

Data Index: 372895 (C4 (Web Text))

Max Activating Token Index: 347

Text #17

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.3218. Min Act: -0.0000

Data Index: 1487692 (Python Code)

Max Activating Token Index: 2

Text #18

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.4007. Min Act: -0.0000

Data Index: 268692 (C4 (Web Text))

Max Activating Token Index: 651

Text #19

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.3226. Min Act: -0.0000

Data Index: 1190075 (C4 (Web Text))

Max Activating Token Index: 969