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

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

Neuron 2443 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1493. Min Range: -1.1493

Max Act: 1.1493. Min Act: -0.0000

Data Index: 1569062 (Python Code)

Max Activating Token Index: 140

Text #1

Max Range: 1.1493. Min Range: -1.1493

Max Act: 1.0152. Min Act: -0.0000

Data Index: 1506829 (Python Code)

Max Activating Token Index: 264

Text #2

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.8745. Min Act: -0.0001

Data Index: 1595483 (Python Code)

Max Activating Token Index: 272

Text #3

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.7922. Min Act: -0.0001

Data Index: 1411558 (Python Code)

Max Activating Token Index: 527

Text #4

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.7877. Min Act: -0.0001

Data Index: 1164332 (C4 (Web Text))

Max Activating Token Index: 920

Text #5

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.7385. Min Act: -0.0001

Data Index: 1633216 (Python Code)

Max Activating Token Index: 705

Text #6

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.7125. Min Act: -0.0001

Data Index: 1587824 (Python Code)

Max Activating Token Index: 592

Text #7

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.6763. Min Act: -0.0001

Data Index: 1547465 (Python Code)

Max Activating Token Index: 761

Text #8

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.7221. Min Act: -0.0000

Data Index: 1516268 (Python Code)

Max Activating Token Index: 238

Text #9

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.6622. Min Act: -0.0001

Data Index: 1491465 (Python Code)

Max Activating Token Index: 869

Text #10

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.6328. Min Act: -0.0001

Data Index: 1208262 (C4 (Web Text))

Max Activating Token Index: 813

Text #11

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.6643. Min Act: -0.0001

Data Index: 1634447 (Python Code)

Max Activating Token Index: 947

Text #12

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.6761. Min Act: -0.0000

Data Index: 1610801 (Python Code)

Max Activating Token Index: 297

Text #13

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.6668. Min Act: -0.0001

Data Index: 1424063 (Python Code)

Max Activating Token Index: 29

Text #14

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.6639. Min Act: -0.0000

Data Index: 1426146 (Python Code)

Max Activating Token Index: 910

Text #15

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.6776. Min Act: -0.0001

Data Index: 1503135 (Python Code)

Max Activating Token Index: 240

Text #16

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.6082. Min Act: -0.0000

Data Index: 1607383 (Python Code)

Max Activating Token Index: 540

Text #17

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.6234. Min Act: -0.0001

Data Index: 1468380 (Python Code)

Max Activating Token Index: 987

Text #18

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.6259. Min Act: -0.0001

Data Index: 484423 (C4 (Web Text))

Max Activating Token Index: 780

Text #19

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.6452. Min Act: -0.0000

Data Index: 1527834 (Python Code)

Max Activating Token Index: 831