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

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

Neuron 2963 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: 0.2545. Min Range: -0.2545

Max Act: 0.2545. Min Act: -0.0001

Data Index: 36453 (C4 (Web Text))

Max Activating Token Index: 715

Text #1

Max Range: 0.2545. Min Range: -0.2545

Max Act: 0.1736. Min Act: -0.0001

Data Index: 4514 (C4 (Web Text))

Max Activating Token Index: 235

Text #2

Max Range: 0.2545. Min Range: -0.2545

Max Act: 0.1689. Min Act: -0.0001

Data Index: 262197 (C4 (Web Text))

Max Activating Token Index: 456

Text #3

Max Range: 0.2545. Min Range: -0.2545

Max Act: 0.1664. Min Act: -0.0001

Data Index: 210580 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 0.2545. Min Range: -0.2545

Max Act: 0.1374. Min Act: -0.0001

Data Index: 579100 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 0.2545. Min Range: -0.2545

Max Act: 0.1322. Min Act: -0.0001

Data Index: 1122457 (C4 (Web Text))

Max Activating Token Index: 646

Text #6

Max Range: 0.2545. Min Range: -0.2545

Max Act: 0.1226. Min Act: -0.0001

Data Index: 89959 (C4 (Web Text))

Max Activating Token Index: 800

Text #7

Max Range: 0.2545. Min Range: -0.2545

Max Act: 0.1228. Min Act: -0.0001

Data Index: 733650 (C4 (Web Text))

Max Activating Token Index: 1014

Text #8

Max Range: 0.2545. Min Range: -0.2545

Max Act: 0.1406. Min Act: -0.0001

Data Index: 508048 (C4 (Web Text))

Max Activating Token Index: 159

Text #9

Max Range: 0.2545. Min Range: -0.2545

Max Act: 0.1304. Min Act: -0.0001

Data Index: 653551 (C4 (Web Text))

Max Activating Token Index: 995

Text #10

Max Range: 0.2545. Min Range: -0.2545

Max Act: 0.1400. Min Act: -0.0001

Data Index: 307002 (C4 (Web Text))

Max Activating Token Index: 841

Text #11

Max Range: 0.2545. Min Range: -0.2545

Max Act: 0.1263. Min Act: -0.0001

Data Index: 402911 (C4 (Web Text))

Max Activating Token Index: 701

Text #12

Max Range: 0.2545. Min Range: -0.2545

Max Act: 0.1262. Min Act: -0.0001

Data Index: 135039 (C4 (Web Text))

Max Activating Token Index: 312

Text #13

Max Range: 0.2545. Min Range: -0.2545

Max Act: 0.1168. Min Act: -0.0001

Data Index: 1250519 (C4 (Web Text))

Max Activating Token Index: 650

Text #14

Max Range: 0.2545. Min Range: -0.2545

Max Act: 0.1190. Min Act: -0.0001

Data Index: 821043 (C4 (Web Text))

Max Activating Token Index: 709

Text #15

Max Range: 0.2545. Min Range: -0.2545

Max Act: 0.1228. Min Act: -0.0001

Data Index: 1069544 (C4 (Web Text))

Max Activating Token Index: 633

Text #16

Max Range: 0.2545. Min Range: -0.2545

Max Act: 0.1223. Min Act: -0.0001

Data Index: 1117494 (C4 (Web Text))

Max Activating Token Index: 256

Text #17

Max Range: 0.2545. Min Range: -0.2545

Max Act: 0.1229. Min Act: -0.0001

Data Index: 884307 (C4 (Web Text))

Max Activating Token Index: 968

Text #18

Max Range: 0.2545. Min Range: -0.2545

Max Act: 0.1211. Min Act: -0.0001

Data Index: 397992 (C4 (Web Text))

Max Activating Token Index: 509

Text #19

Max Range: 0.2545. Min Range: -0.2545

Max Act: 0.1216. Min Act: -0.0001

Data Index: 34874 (C4 (Web Text))

Max Activating Token Index: 709