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

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

Neuron 3124 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1493. Min Act: -0.0001

Data Index: 733241 (C4 (Web Text))

Max Activating Token Index: 203

Text #1

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1561. Min Act: -0.0001

Data Index: 437501 (C4 (Web Text))

Max Activating Token Index: 147

Text #2

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1346. Min Act: -0.0001

Data Index: 403255 (C4 (Web Text))

Max Activating Token Index: 813

Text #3

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1326. Min Act: -0.0001

Data Index: 1268732 (C4 (Web Text))

Max Activating Token Index: 411

Text #4

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1306. Min Act: -0.0001

Data Index: 560878 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1339. Min Act: -0.0001

Data Index: 194042 (C4 (Web Text))

Max Activating Token Index: 132

Text #6

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1331. Min Act: -0.0001

Data Index: 571873 (C4 (Web Text))

Max Activating Token Index: 566

Text #7

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1350. Min Act: -0.0001

Data Index: 259383 (C4 (Web Text))

Max Activating Token Index: 520

Text #8

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1255. Min Act: -0.0001

Data Index: 1333551 (C4 (Web Text))

Max Activating Token Index: 789

Text #9

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1276. Min Act: -0.0001

Data Index: 621823 (C4 (Web Text))

Max Activating Token Index: 839

Text #10

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1237. Min Act: -0.0001

Data Index: 1238516 (C4 (Web Text))

Max Activating Token Index: 819

Text #11

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1333. Min Act: -0.0001

Data Index: 1103855 (C4 (Web Text))

Max Activating Token Index: 174

Text #12

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1251. Min Act: -0.0001

Data Index: 631279 (C4 (Web Text))

Max Activating Token Index: 513

Text #13

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1282. Min Act: -0.0001

Data Index: 385201 (C4 (Web Text))

Max Activating Token Index: 715

Text #14

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1138. Min Act: -0.0001

Data Index: 536663 (C4 (Web Text))

Max Activating Token Index: 807

Text #15

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1205. Min Act: -0.0001

Data Index: 1335746 (C4 (Web Text))

Max Activating Token Index: 232

Text #16

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1175. Min Act: -0.0001

Data Index: 802082 (C4 (Web Text))

Max Activating Token Index: 947

Text #17

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1129. Min Act: -0.0001

Data Index: 133991 (C4 (Web Text))

Max Activating Token Index: 104

Text #18

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1135. Min Act: -0.0001

Data Index: 1263749 (C4 (Web Text))

Max Activating Token Index: 442

Text #19

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1124. Min Act: -0.0001

Data Index: 711750 (C4 (Web Text))

Max Activating Token Index: 723