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

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

Neuron 2951 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1519. Min Range: -0.1519

Max Act: 0.1519. Min Act: -0.0000

Data Index: 401382 (C4 (Web Text))

Max Activating Token Index: 560

Text #1

Max Range: 0.1519. Min Range: -0.1519

Max Act: 0.1314. Min Act: -0.0000

Data Index: 994501 (C4 (Web Text))

Max Activating Token Index: 751

Text #2

Max Range: 0.1519. Min Range: -0.1519

Max Act: 0.1238. Min Act: -0.0000

Data Index: 507663 (C4 (Web Text))

Max Activating Token Index: 745

Text #3

Max Range: 0.1519. Min Range: -0.1519

Max Act: 0.1438. Min Act: -0.0000

Data Index: 1497495 (Python Code)

Max Activating Token Index: 186

Text #4

Max Range: 0.1519. Min Range: -0.1519

Max Act: 0.1329. Min Act: -0.0001

Data Index: 393094 (C4 (Web Text))

Max Activating Token Index: 184

Text #5

Max Range: 0.1519. Min Range: -0.1519

Max Act: 0.1268. Min Act: -0.0001

Data Index: 371457 (C4 (Web Text))

Max Activating Token Index: 613

Text #6

Max Range: 0.1519. Min Range: -0.1519

Max Act: 0.1149. Min Act: -0.0001

Data Index: 678177 (C4 (Web Text))

Max Activating Token Index: 832

Text #7

Max Range: 0.1519. Min Range: -0.1519

Max Act: 0.1172. Min Act: -0.0000

Data Index: 1091867 (C4 (Web Text))

Max Activating Token Index: 566

Text #8

Max Range: 0.1519. Min Range: -0.1519

Max Act: 0.1285. Min Act: -0.0001

Data Index: 1356528 (C4 (Web Text))

Max Activating Token Index: 1009

Text #9

Max Range: 0.1519. Min Range: -0.1519

Max Act: 0.1280. Min Act: -0.0001

Data Index: 969116 (C4 (Web Text))

Max Activating Token Index: 661

Text #10

Max Range: 0.1519. Min Range: -0.1519

Max Act: 0.1270. Min Act: -0.0000

Data Index: 1419769 (Python Code)

Max Activating Token Index: 392

Text #11

Max Range: 0.1519. Min Range: -0.1519

Max Act: 0.1091. Min Act: -0.0000

Data Index: 833545 (C4 (Web Text))

Max Activating Token Index: 1020

Text #12

Max Range: 0.1519. Min Range: -0.1519

Max Act: 0.1146. Min Act: -0.0001

Data Index: 893662 (C4 (Web Text))

Max Activating Token Index: 984

Text #13

Max Range: 0.1519. Min Range: -0.1519

Max Act: 0.1137. Min Act: -0.0001

Data Index: 1191356 (C4 (Web Text))

Max Activating Token Index: 533

Text #14

Max Range: 0.1519. Min Range: -0.1519

Max Act: 0.1148. Min Act: -0.0000

Data Index: 1232616 (C4 (Web Text))

Max Activating Token Index: 47

Text #15

Max Range: 0.1519. Min Range: -0.1519

Max Act: 0.1188. Min Act: -0.0000

Data Index: 455095 (C4 (Web Text))

Max Activating Token Index: 690

Text #16

Max Range: 0.1519. Min Range: -0.1519

Max Act: 0.1158. Min Act: -0.0001

Data Index: 1259789 (C4 (Web Text))

Max Activating Token Index: 32

Text #17

Max Range: 0.1519. Min Range: -0.1519

Max Act: 0.1023. Min Act: -0.0001

Data Index: 348431 (C4 (Web Text))

Max Activating Token Index: 744

Text #18

Max Range: 0.1519. Min Range: -0.1519

Max Act: 0.1118. Min Act: -0.0000

Data Index: 440019 (C4 (Web Text))

Max Activating Token Index: 476

Text #19

Max Range: 0.1519. Min Range: -0.1519

Max Act: 0.1124. Min Act: -0.0001

Data Index: 222477 (C4 (Web Text))

Max Activating Token Index: 332