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

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

Neuron 598 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9226. Min Range: -1.9226

Max Act: 1.8721. Min Act: -0.0001

Data Index: 185168 (C4 (Web Text))

Max Activating Token Index: 62

Text #1

Max Range: 1.9226. Min Range: -1.9226

Max Act: 1.9226. Min Act: -0.0001

Data Index: 1369360 (Python Code)

Max Activating Token Index: 569

Text #2

Max Range: 1.9226. Min Range: -1.9226

Max Act: 1.8900. Min Act: -0.0000

Data Index: 616643 (C4 (Web Text))

Max Activating Token Index: 113

Text #3

Max Range: 1.9226. Min Range: -1.9226

Max Act: 1.9041. Min Act: -0.0001

Data Index: 612399 (C4 (Web Text))

Max Activating Token Index: 451

Text #4

Max Range: 1.9226. Min Range: -1.9226

Max Act: 1.7427. Min Act: -0.0001

Data Index: 1245069 (C4 (Web Text))

Max Activating Token Index: 257

Text #5

Max Range: 1.9226. Min Range: -1.9226

Max Act: 1.5885. Min Act: -0.0001

Data Index: 459823 (C4 (Web Text))

Max Activating Token Index: 928

Text #6

Max Range: 1.9226. Min Range: -1.9226

Max Act: 1.8180. Min Act: -0.0001

Data Index: 1643968 (Python Code)

Max Activating Token Index: 257

Text #7

Max Range: 1.9226. Min Range: -1.9226

Max Act: 1.6361. Min Act: -0.0001

Data Index: 1303114 (C4 (Web Text))

Max Activating Token Index: 919

Text #8

Max Range: 1.9226. Min Range: -1.9226

Max Act: 1.7173. Min Act: -0.0000

Data Index: 1562276 (Python Code)

Max Activating Token Index: 865

Text #9

Max Range: 1.9226. Min Range: -1.9226

Max Act: 1.6027. Min Act: -0.0000

Data Index: 1493839 (Python Code)

Max Activating Token Index: 413

Text #10

Max Range: 1.9226. Min Range: -1.9226

Max Act: 1.6013. Min Act: -0.0000

Data Index: 1583066 (Python Code)

Max Activating Token Index: 113

Text #11

Max Range: 1.9226. Min Range: -1.9226

Max Act: 1.7036. Min Act: -0.0001

Data Index: 1558205 (Python Code)

Max Activating Token Index: 638

Text #12

Max Range: 1.9226. Min Range: -1.9226

Max Act: 1.7584. Min Act: -0.0001

Data Index: 549995 (C4 (Web Text))

Max Activating Token Index: 209

Text #13

Max Range: 1.9226. Min Range: -1.9226

Max Act: 1.6286. Min Act: -0.0001

Data Index: 830916 (C4 (Web Text))

Max Activating Token Index: 896

Text #14

Max Range: 1.9226. Min Range: -1.9226

Max Act: 1.5394. Min Act: -0.0001

Data Index: 442631 (C4 (Web Text))

Max Activating Token Index: 20

Text #15

Max Range: 1.9226. Min Range: -1.9226

Max Act: 1.5353. Min Act: -0.0001

Data Index: 1355288 (C4 (Web Text))

Max Activating Token Index: 406

Text #16

Max Range: 1.9226. Min Range: -1.9226

Max Act: 1.6234. Min Act: -0.0001

Data Index: 933963 (C4 (Web Text))

Max Activating Token Index: 518

Text #17

Max Range: 1.9226. Min Range: -1.9226

Max Act: 1.6946. Min Act: -0.0001

Data Index: 577985 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 1.9226. Min Range: -1.9226

Max Act: 1.6904. Min Act: -0.0000

Data Index: 1593404 (Python Code)

Max Activating Token Index: 185

Text #19

Max Range: 1.9226. Min Range: -1.9226

Max Act: 1.5174. Min Act: -0.0000

Data Index: 1494226 (Python Code)

Max Activating Token Index: 113