Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1408 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1885. Min Act: -0.0002

Data Index: 1276496 (C4 (Web Text))

Max Activating Token Index: 397

Text #1

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1938. Min Act: -0.0001

Data Index: 912265 (C4 (Web Text))

Max Activating Token Index: 299

Text #2

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1481. Min Act: -0.0002

Data Index: 474866 (C4 (Web Text))

Max Activating Token Index: 752

Text #3

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1659. Min Act: -0.0001

Data Index: 1027696 (C4 (Web Text))

Max Activating Token Index: 592

Text #4

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1328. Min Act: -0.0002

Data Index: 1132140 (C4 (Web Text))

Max Activating Token Index: 655

Text #5

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1345. Min Act: -0.0002

Data Index: 1117378 (C4 (Web Text))

Max Activating Token Index: 313

Text #6

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1428. Min Act: -0.0001

Data Index: 513225 (C4 (Web Text))

Max Activating Token Index: 13

Text #7

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1373. Min Act: -0.0002

Data Index: 81995 (C4 (Web Text))

Max Activating Token Index: 442

Text #8

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1353. Min Act: -0.0002

Data Index: 896763 (C4 (Web Text))

Max Activating Token Index: 13

Text #9

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1308. Min Act: -0.0001

Data Index: 1078706 (C4 (Web Text))

Max Activating Token Index: 154

Text #10

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1564. Min Act: -0.0002

Data Index: 830361 (C4 (Web Text))

Max Activating Token Index: 572

Text #11

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1182. Min Act: -0.0002

Data Index: 165658 (C4 (Web Text))

Max Activating Token Index: 367

Text #12

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1356. Min Act: -0.0001

Data Index: 544325 (C4 (Web Text))

Max Activating Token Index: 260

Text #13

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1249. Min Act: -0.0002

Data Index: 728362 (C4 (Web Text))

Max Activating Token Index: 12

Text #14

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1297. Min Act: -0.0002

Data Index: 688259 (C4 (Web Text))

Max Activating Token Index: 978

Text #15

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1251. Min Act: -0.0002

Data Index: 1311711 (C4 (Web Text))

Max Activating Token Index: 215

Text #16

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1151. Min Act: -0.0002

Data Index: 353780 (C4 (Web Text))

Max Activating Token Index: 128

Text #17

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1378. Min Act: -0.0001

Data Index: 615788 (C4 (Web Text))

Max Activating Token Index: 597

Text #18

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1190. Min Act: -0.0002

Data Index: 991563 (C4 (Web Text))

Max Activating Token Index: 938

Text #19

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1145. Min Act: -0.0002

Data Index: 1251202 (C4 (Web Text))

Max Activating Token Index: 905