Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1121 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1444. Min Act: -0.0003

Data Index: 680829 (C4 (Web Text))

Max Activating Token Index: 285

Text #1

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1373. Min Act: -0.0003

Data Index: 621774 (C4 (Web Text))

Max Activating Token Index: 88

Text #2

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1235. Min Act: -0.0002

Data Index: 570355 (C4 (Web Text))

Max Activating Token Index: 831

Text #3

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1200. Min Act: -0.0003

Data Index: 1190827 (C4 (Web Text))

Max Activating Token Index: 525

Text #4

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1168. Min Act: -0.0001

Data Index: 337308 (C4 (Web Text))

Max Activating Token Index: 591

Text #5

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1152. Min Act: -0.0003

Data Index: 627416 (C4 (Web Text))

Max Activating Token Index: 161

Text #6

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1115. Min Act: -0.0003

Data Index: 787494 (C4 (Web Text))

Max Activating Token Index: 680

Text #7

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1105. Min Act: -0.0000

Data Index: 529561 (C4 (Web Text))

Max Activating Token Index: 1010

Text #8

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1051. Min Act: -0.0001

Data Index: 181684 (C4 (Web Text))

Max Activating Token Index: 697

Text #9

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1068. Min Act: -0.0001

Data Index: 617375 (C4 (Web Text))

Max Activating Token Index: 296

Text #10

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1041. Min Act: -0.0003

Data Index: 497301 (C4 (Web Text))

Max Activating Token Index: 341

Text #11

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1036. Min Act: -0.0003

Data Index: 108198 (C4 (Web Text))

Max Activating Token Index: 715

Text #12

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1024. Min Act: -0.0003

Data Index: 729248 (C4 (Web Text))

Max Activating Token Index: 300

Text #13

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1041. Min Act: -0.0003

Data Index: 695209 (C4 (Web Text))

Max Activating Token Index: 600

Text #14

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1008. Min Act: -0.0003

Data Index: 986178 (C4 (Web Text))

Max Activating Token Index: 13

Text #15

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0991. Min Act: -0.0003

Data Index: 1268965 (C4 (Web Text))

Max Activating Token Index: 523

Text #16

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0992. Min Act: -0.0002

Data Index: 679856 (C4 (Web Text))

Max Activating Token Index: 441

Text #17

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0992. Min Act: -0.0003

Data Index: 113110 (C4 (Web Text))

Max Activating Token Index: 821

Text #18

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0988. Min Act: -0.0003

Data Index: 649089 (C4 (Web Text))

Max Activating Token Index: 399

Text #19

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0965. Min Act: -0.0002

Data Index: 133419 (C4 (Web Text))

Max Activating Token Index: 510