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

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

Neuron 2346 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2460. Min Range: -0.2460

Max Act: 0.2460. Min Act: -0.0000

Data Index: 946753 (C4 (Web Text))

Max Activating Token Index: 552

Text #1

Max Range: 0.2460. Min Range: -0.2460

Max Act: 0.1813. Min Act: -0.0000

Data Index: 938021 (C4 (Web Text))

Max Activating Token Index: 842

Text #2

Max Range: 0.2460. Min Range: -0.2460

Max Act: 0.1660. Min Act: -0.0000

Data Index: 637143 (C4 (Web Text))

Max Activating Token Index: 349

Text #3

Max Range: 0.2460. Min Range: -0.2460

Max Act: 0.1455. Min Act: -0.0000

Data Index: 625377 (C4 (Web Text))

Max Activating Token Index: 400

Text #4

Max Range: 0.2460. Min Range: -0.2460

Max Act: 0.1428. Min Act: -0.0000

Data Index: 666566 (C4 (Web Text))

Max Activating Token Index: 421

Text #5

Max Range: 0.2460. Min Range: -0.2460

Max Act: 0.1388. Min Act: -0.0000

Data Index: 298864 (C4 (Web Text))

Max Activating Token Index: 730

Text #6

Max Range: 0.2460. Min Range: -0.2460

Max Act: 0.1362. Min Act: -0.0000

Data Index: 468689 (C4 (Web Text))

Max Activating Token Index: 444

Text #7

Max Range: 0.2460. Min Range: -0.2460

Max Act: 0.1319. Min Act: -0.0000

Data Index: 1078012 (C4 (Web Text))

Max Activating Token Index: 821

Text #8

Max Range: 0.2460. Min Range: -0.2460

Max Act: 0.1298. Min Act: -0.0000

Data Index: 402507 (C4 (Web Text))

Max Activating Token Index: 762

Text #9

Max Range: 0.2460. Min Range: -0.2460

Max Act: 0.1364. Min Act: -0.0000

Data Index: 737037 (C4 (Web Text))

Max Activating Token Index: 755

Text #10

Max Range: 0.2460. Min Range: -0.2460

Max Act: 0.1221. Min Act: -0.0000

Data Index: 1030368 (C4 (Web Text))

Max Activating Token Index: 892

Text #11

Max Range: 0.2460. Min Range: -0.2460

Max Act: 0.1290. Min Act: -0.0000

Data Index: 1067814 (C4 (Web Text))

Max Activating Token Index: 965

Text #12

Max Range: 0.2460. Min Range: -0.2460

Max Act: 0.1320. Min Act: -0.0000

Data Index: 876680 (C4 (Web Text))

Max Activating Token Index: 737

Text #13

Max Range: 0.2460. Min Range: -0.2460

Max Act: 0.1151. Min Act: -0.0000

Data Index: 1435761 (Python Code)

Max Activating Token Index: 823

Text #14

Max Range: 0.2460. Min Range: -0.2460

Max Act: 0.1173. Min Act: -0.0000

Data Index: 242216 (C4 (Web Text))

Max Activating Token Index: 890

Text #15

Max Range: 0.2460. Min Range: -0.2460

Max Act: 0.1163. Min Act: -0.0000

Data Index: 1091240 (C4 (Web Text))

Max Activating Token Index: 352

Text #16

Max Range: 0.2460. Min Range: -0.2460

Max Act: 0.1067. Min Act: -0.0000

Data Index: 820930 (C4 (Web Text))

Max Activating Token Index: 295

Text #17

Max Range: 0.2460. Min Range: -0.2460

Max Act: 0.0988. Min Act: -0.0000

Data Index: 1267540 (C4 (Web Text))

Max Activating Token Index: 871

Text #18

Max Range: 0.2460. Min Range: -0.2460

Max Act: 0.1144. Min Act: -0.0000

Data Index: 1016415 (C4 (Web Text))

Max Activating Token Index: 385

Text #19

Max Range: 0.2460. Min Range: -0.2460

Max Act: 0.1151. Min Act: -0.0000

Data Index: 410633 (C4 (Web Text))

Max Activating Token Index: 673