Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2489 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0183. Min Range: -1.0183

Max Act: 1.0183. Min Act: -0.0001

Data Index: 108194 (C4 (Web Text))

Max Activating Token Index: 125

Text #1

Max Range: 1.0183. Min Range: -1.0183

Max Act: 0.8546. Min Act: -0.0001

Data Index: 826738 (C4 (Web Text))

Max Activating Token Index: 350

Text #2

Max Range: 1.0183. Min Range: -1.0183

Max Act: 0.9129. Min Act: -0.0001

Data Index: 989138 (C4 (Web Text))

Max Activating Token Index: 993

Text #3

Max Range: 1.0183. Min Range: -1.0183

Max Act: 0.8677. Min Act: -0.0001

Data Index: 704700 (C4 (Web Text))

Max Activating Token Index: 579

Text #4

Max Range: 1.0183. Min Range: -1.0183

Max Act: 0.8335. Min Act: -0.0001

Data Index: 1019364 (C4 (Web Text))

Max Activating Token Index: 936

Text #5

Max Range: 1.0183. Min Range: -1.0183

Max Act: 0.7486. Min Act: -0.0001

Data Index: 170519 (C4 (Web Text))

Max Activating Token Index: 962

Text #6

Max Range: 1.0183. Min Range: -1.0183

Max Act: 0.7787. Min Act: -0.0001

Data Index: 1327024 (C4 (Web Text))

Max Activating Token Index: 538

Text #7

Max Range: 1.0183. Min Range: -1.0183

Max Act: 0.6858. Min Act: -0.0001

Data Index: 1170046 (C4 (Web Text))

Max Activating Token Index: 592

Text #8

Max Range: 1.0183. Min Range: -1.0183

Max Act: 0.6940. Min Act: -0.0001

Data Index: 73660 (C4 (Web Text))

Max Activating Token Index: 296

Text #9

Max Range: 1.0183. Min Range: -1.0183

Max Act: 0.6210. Min Act: -0.0001

Data Index: 781407 (C4 (Web Text))

Max Activating Token Index: 296

Text #10

Max Range: 1.0183. Min Range: -1.0183

Max Act: 0.6384. Min Act: -0.0001

Data Index: 1166118 (C4 (Web Text))

Max Activating Token Index: 253

Text #11

Max Range: 1.0183. Min Range: -1.0183

Max Act: 0.6387. Min Act: -0.0001

Data Index: 1267299 (C4 (Web Text))

Max Activating Token Index: 745

Text #12

Max Range: 1.0183. Min Range: -1.0183

Max Act: 0.6287. Min Act: -0.0001

Data Index: 1255869 (C4 (Web Text))

Max Activating Token Index: 799

Text #13

Max Range: 1.0183. Min Range: -1.0183

Max Act: 0.6104. Min Act: -0.0001

Data Index: 904062 (C4 (Web Text))

Max Activating Token Index: 471

Text #14

Max Range: 1.0183. Min Range: -1.0183

Max Act: 0.5965. Min Act: -0.0001

Data Index: 165680 (C4 (Web Text))

Max Activating Token Index: 471

Text #15

Max Range: 1.0183. Min Range: -1.0183

Max Act: 0.6347. Min Act: -0.0001

Data Index: 1148426 (C4 (Web Text))

Max Activating Token Index: 25

Text #16

Max Range: 1.0183. Min Range: -1.0183

Max Act: 0.5544. Min Act: -0.0001

Data Index: 1315344 (C4 (Web Text))

Max Activating Token Index: 506

Text #17

Max Range: 1.0183. Min Range: -1.0183

Max Act: 0.5427. Min Act: -0.0001

Data Index: 338676 (C4 (Web Text))

Max Activating Token Index: 79

Text #18

Max Range: 1.0183. Min Range: -1.0183

Max Act: 0.5344. Min Act: -0.0001

Data Index: 764095 (C4 (Web Text))

Max Activating Token Index: 309

Text #19

Max Range: 1.0183. Min Range: -1.0183

Max Act: 0.5318. Min Act: -0.0001

Data Index: 456095 (C4 (Web Text))

Max Activating Token Index: 93