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

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

Neuron 2612 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5204. Min Range: -1.5204

Max Act: 1.4363. Min Act: -0.0001

Data Index: 132280 (C4 (Web Text))

Max Activating Token Index: 290

Text #1

Max Range: 1.5204. Min Range: -1.5204

Max Act: 1.4874. Min Act: -0.0001

Data Index: 1027441 (C4 (Web Text))

Max Activating Token Index: 781

Text #2

Max Range: 1.5204. Min Range: -1.5204

Max Act: 1.5204. Min Act: -0.0001

Data Index: 1271445 (C4 (Web Text))

Max Activating Token Index: 604

Text #3

Max Range: 1.5204. Min Range: -1.5204

Max Act: 1.4574. Min Act: -0.0001

Data Index: 225391 (C4 (Web Text))

Max Activating Token Index: 571

Text #4

Max Range: 1.5204. Min Range: -1.5204

Max Act: 1.4466. Min Act: -0.0001

Data Index: 645602 (C4 (Web Text))

Max Activating Token Index: 354

Text #5

Max Range: 1.5204. Min Range: -1.5204

Max Act: 1.3298. Min Act: -0.0001

Data Index: 1120942 (C4 (Web Text))

Max Activating Token Index: 391

Text #6

Max Range: 1.5204. Min Range: -1.5204

Max Act: 1.4167. Min Act: -0.0001

Data Index: 389849 (C4 (Web Text))

Max Activating Token Index: 231

Text #7

Max Range: 1.5204. Min Range: -1.5204

Max Act: 1.3567. Min Act: -0.0001

Data Index: 507805 (C4 (Web Text))

Max Activating Token Index: 794

Text #8

Max Range: 1.5204. Min Range: -1.5204

Max Act: 1.3408. Min Act: -0.0001

Data Index: 1265778 (C4 (Web Text))

Max Activating Token Index: 502

Text #9

Max Range: 1.5204. Min Range: -1.5204

Max Act: 1.3724. Min Act: -0.0001

Data Index: 52331 (C4 (Web Text))

Max Activating Token Index: 429

Text #10

Max Range: 1.5204. Min Range: -1.5204

Max Act: 1.3322. Min Act: -0.0001

Data Index: 702073 (C4 (Web Text))

Max Activating Token Index: 979

Text #11

Max Range: 1.5204. Min Range: -1.5204

Max Act: 1.3446. Min Act: -0.0001

Data Index: 1115590 (C4 (Web Text))

Max Activating Token Index: 646

Text #12

Max Range: 1.5204. Min Range: -1.5204

Max Act: 1.3372. Min Act: -0.0001

Data Index: 1019211 (C4 (Web Text))

Max Activating Token Index: 514

Text #13

Max Range: 1.5204. Min Range: -1.5204

Max Act: 1.2980. Min Act: -0.0001

Data Index: 976946 (C4 (Web Text))

Max Activating Token Index: 17

Text #14

Max Range: 1.5204. Min Range: -1.5204

Max Act: 1.2802. Min Act: -0.0001

Data Index: 42711 (C4 (Web Text))

Max Activating Token Index: 927

Text #15

Max Range: 1.5204. Min Range: -1.5204

Max Act: 1.3420. Min Act: -0.0001

Data Index: 791018 (C4 (Web Text))

Max Activating Token Index: 638

Text #16

Max Range: 1.5204. Min Range: -1.5204

Max Act: 1.2107. Min Act: -0.0001

Data Index: 1253234 (C4 (Web Text))

Max Activating Token Index: 768

Text #17

Max Range: 1.5204. Min Range: -1.5204

Max Act: 1.1891. Min Act: -0.0001

Data Index: 437079 (C4 (Web Text))

Max Activating Token Index: 552

Text #18

Max Range: 1.5204. Min Range: -1.5204

Max Act: 1.1001. Min Act: -0.0001

Data Index: 953489 (C4 (Web Text))

Max Activating Token Index: 217

Text #19

Max Range: 1.5204. Min Range: -1.5204

Max Act: 1.2943. Min Act: -0.0001

Data Index: 1161579 (C4 (Web Text))

Max Activating Token Index: 308