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

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

Neuron 953 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.7220. Min Act: -0.0003

Data Index: 1134047 (C4 (Web Text))

Max Activating Token Index: 740

Text #1

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.7287. Min Act: -0.0003

Data Index: 276564 (C4 (Web Text))

Max Activating Token Index: 188

Text #2

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.6777. Min Act: -0.0003

Data Index: 1110605 (C4 (Web Text))

Max Activating Token Index: 400

Text #3

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.6980. Min Act: -0.0003

Data Index: 82127 (C4 (Web Text))

Max Activating Token Index: 611

Text #4

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.6840. Min Act: -0.0003

Data Index: 944616 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.6854. Min Act: -0.0003

Data Index: 806557 (C4 (Web Text))

Max Activating Token Index: 701

Text #6

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.6579. Min Act: -0.0003

Data Index: 105904 (C4 (Web Text))

Max Activating Token Index: 527

Text #7

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.6951. Min Act: -0.0003

Data Index: 1190524 (C4 (Web Text))

Max Activating Token Index: 533

Text #8

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.6507. Min Act: -0.0003

Data Index: 130599 (C4 (Web Text))

Max Activating Token Index: 608

Text #9

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.6843. Min Act: -0.0003

Data Index: 336040 (C4 (Web Text))

Max Activating Token Index: 750

Text #10

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.6452. Min Act: -0.0003

Data Index: 676763 (C4 (Web Text))

Max Activating Token Index: 56

Text #11

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.5638. Min Act: -0.0003

Data Index: 1239244 (C4 (Web Text))

Max Activating Token Index: 312

Text #12

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.6305. Min Act: -0.0003

Data Index: 484723 (C4 (Web Text))

Max Activating Token Index: 142

Text #13

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.6438. Min Act: -0.0003

Data Index: 899038 (C4 (Web Text))

Max Activating Token Index: 20

Text #14

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.6209. Min Act: -0.0003

Data Index: 1070717 (C4 (Web Text))

Max Activating Token Index: 442

Text #15

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.5831. Min Act: -0.0003

Data Index: 1072298 (C4 (Web Text))

Max Activating Token Index: 303

Text #16

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.6394. Min Act: -0.0003

Data Index: 235107 (C4 (Web Text))

Max Activating Token Index: 382

Text #17

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.6382. Min Act: -0.0003

Data Index: 554815 (C4 (Web Text))

Max Activating Token Index: 471

Text #18

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.6154. Min Act: -0.0003

Data Index: 768992 (C4 (Web Text))

Max Activating Token Index: 544

Text #19

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.6555. Min Act: -0.0003

Data Index: 62148 (C4 (Web Text))

Max Activating Token Index: 117