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

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

Neuron 4830 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6986. Min Range: -1.6986

Max Act: 1.6986. Min Act: -0.0000

Data Index: 1522685 (Python Code)

Max Activating Token Index: 455

Text #1

Max Range: 1.6986. Min Range: -1.6986

Max Act: 1.4437. Min Act: -0.0000

Data Index: 1579297 (Python Code)

Max Activating Token Index: 487

Text #2

Max Range: 1.6986. Min Range: -1.6986

Max Act: 1.3311. Min Act: -0.0000

Data Index: 1408121 (Python Code)

Max Activating Token Index: 668

Text #3

Max Range: 1.6986. Min Range: -1.6986

Max Act: 1.3489. Min Act: -0.0000

Data Index: 1509508 (Python Code)

Max Activating Token Index: 1022

Text #4

Max Range: 1.6986. Min Range: -1.6986

Max Act: 1.2054. Min Act: -0.0000

Data Index: 1390320 (Python Code)

Max Activating Token Index: 940

Text #5

Max Range: 1.6986. Min Range: -1.6986

Max Act: 1.1993. Min Act: -0.0000

Data Index: 1444296 (Python Code)

Max Activating Token Index: 161

Text #6

Max Range: 1.6986. Min Range: -1.6986

Max Act: 1.1968. Min Act: -0.0000

Data Index: 1401632 (Python Code)

Max Activating Token Index: 1020

Text #7

Max Range: 1.6986. Min Range: -1.6986

Max Act: 1.1978. Min Act: -0.0000

Data Index: 1488567 (Python Code)

Max Activating Token Index: 430

Text #8

Max Range: 1.6986. Min Range: -1.6986

Max Act: 1.1230. Min Act: -0.0000

Data Index: 1604756 (Python Code)

Max Activating Token Index: 10

Text #9

Max Range: 1.6986. Min Range: -1.6986

Max Act: 1.1230. Min Act: -0.0000

Data Index: 1575499 (Python Code)

Max Activating Token Index: 10

Text #10

Max Range: 1.6986. Min Range: -1.6986

Max Act: 1.1155. Min Act: -0.0000

Data Index: 1422462 (Python Code)

Max Activating Token Index: 9

Text #11

Max Range: 1.6986. Min Range: -1.6986

Max Act: 1.1825. Min Act: -0.0000

Data Index: 1454634 (Python Code)

Max Activating Token Index: 912

Text #12

Max Range: 1.6986. Min Range: -1.6986

Max Act: 1.1649. Min Act: -0.0000

Data Index: 1644677 (Python Code)

Max Activating Token Index: 676

Text #13

Max Range: 1.6986. Min Range: -1.6986

Max Act: 1.1621. Min Act: -0.0000

Data Index: 1475050 (Python Code)

Max Activating Token Index: 245

Text #14

Max Range: 1.6986. Min Range: -1.6986

Max Act: 1.1215. Min Act: -0.0000

Data Index: 1426821 (Python Code)

Max Activating Token Index: 736

Text #15

Max Range: 1.6986. Min Range: -1.6986

Max Act: 1.1388. Min Act: -0.0000

Data Index: 1545615 (Python Code)

Max Activating Token Index: 117

Text #16

Max Range: 1.6986. Min Range: -1.6986

Max Act: 1.0416. Min Act: -0.0000

Data Index: 1528527 (Python Code)

Max Activating Token Index: 70

Text #17

Max Range: 1.6986. Min Range: -1.6986

Max Act: 1.1691. Min Act: -0.0000

Data Index: 1472988 (Python Code)

Max Activating Token Index: 1008

Text #18

Max Range: 1.6986. Min Range: -1.6986

Max Act: 1.0747. Min Act: -0.0000

Data Index: 1562564 (Python Code)

Max Activating Token Index: 394

Text #19

Max Range: 1.6986. Min Range: -1.6986

Max Act: 0.9961. Min Act: -0.0000

Data Index: 1540470 (Python Code)

Max Activating Token Index: 659