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

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

Neuron 986 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.6694. Min Act: -0.0000

Data Index: 1407561 (Python Code)

Max Activating Token Index: 428

Text #1

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.5701. Min Act: -0.0000

Data Index: 1629648 (Python Code)

Max Activating Token Index: 81

Text #2

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.4503. Min Act: -0.0001

Data Index: 1542020 (Python Code)

Max Activating Token Index: 420

Text #3

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.4339. Min Act: -0.0000

Data Index: 1655759 (Python Code)

Max Activating Token Index: 251

Text #4

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.4304. Min Act: -0.0000

Data Index: 1656353 (Python Code)

Max Activating Token Index: 559

Text #5

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.3402. Min Act: -0.0000

Data Index: 1426394 (Python Code)

Max Activating Token Index: 163

Text #6

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.3203. Min Act: -0.0000

Data Index: 1431449 (Python Code)

Max Activating Token Index: 530

Text #7

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.3183. Min Act: -0.0001

Data Index: 1451826 (Python Code)

Max Activating Token Index: 530

Text #8

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.3215. Min Act: -0.0001

Data Index: 1523509 (Python Code)

Max Activating Token Index: 698

Text #9

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.3017. Min Act: -0.0001

Data Index: 1390159 (Python Code)

Max Activating Token Index: 804

Text #10

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.3080. Min Act: -0.0000

Data Index: 1577263 (Python Code)

Max Activating Token Index: 264

Text #11

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.3264. Min Act: -0.0000

Data Index: 1492368 (Python Code)

Max Activating Token Index: 514

Text #12

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.3033. Min Act: -0.0001

Data Index: 1654869 (Python Code)

Max Activating Token Index: 410

Text #13

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.3088. Min Act: -0.0000

Data Index: 1406473 (Python Code)

Max Activating Token Index: 1019

Text #14

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.3047. Min Act: -0.0000

Data Index: 1552750 (Python Code)

Max Activating Token Index: 284

Text #15

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.2767. Min Act: -0.0001

Data Index: 1363989 (Python Code)

Max Activating Token Index: 226

Text #16

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.2774. Min Act: -0.0001

Data Index: 1547924 (Python Code)

Max Activating Token Index: 975

Text #17

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.2838. Min Act: -0.0001

Data Index: 1377275 (Python Code)

Max Activating Token Index: 342

Text #18

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.3136. Min Act: -0.0001

Data Index: 1604289 (Python Code)

Max Activating Token Index: 250

Text #19

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.3037. Min Act: -0.0001

Data Index: 1645460 (Python Code)

Max Activating Token Index: 855