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

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

Neuron 2116 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6195. Min Range: -0.6195

Max Act: 0.6195. Min Act: -0.0001

Data Index: 1457901 (Python Code)

Max Activating Token Index: 193

Text #1

Max Range: 0.6195. Min Range: -0.6195

Max Act: 0.5859. Min Act: -0.0001

Data Index: 1380571 (Python Code)

Max Activating Token Index: 371

Text #2

Max Range: 0.6195. Min Range: -0.6195

Max Act: 0.4969. Min Act: -0.0001

Data Index: 1573988 (Python Code)

Max Activating Token Index: 171

Text #3

Max Range: 0.6195. Min Range: -0.6195

Max Act: 0.5071. Min Act: -0.0001

Data Index: 1586176 (Python Code)

Max Activating Token Index: 1021

Text #4

Max Range: 0.6195. Min Range: -0.6195

Max Act: 0.5069. Min Act: -0.0001

Data Index: 1572990 (Python Code)

Max Activating Token Index: 783

Text #5

Max Range: 0.6195. Min Range: -0.6195

Max Act: 0.4868. Min Act: -0.0001

Data Index: 1411953 (Python Code)

Max Activating Token Index: 901

Text #6

Max Range: 0.6195. Min Range: -0.6195

Max Act: 0.5117. Min Act: -0.0001

Data Index: 1450933 (Python Code)

Max Activating Token Index: 915

Text #7

Max Range: 0.6195. Min Range: -0.6195

Max Act: 0.4887. Min Act: -0.0001

Data Index: 1363832 (Python Code)

Max Activating Token Index: 193

Text #8

Max Range: 0.6195. Min Range: -0.6195

Max Act: 0.4714. Min Act: -0.0001

Data Index: 1537259 (Python Code)

Max Activating Token Index: 788

Text #9

Max Range: 0.6195. Min Range: -0.6195

Max Act: 0.4847. Min Act: -0.0001

Data Index: 1443007 (Python Code)

Max Activating Token Index: 356

Text #10

Max Range: 0.6195. Min Range: -0.6195

Max Act: 0.4870. Min Act: -0.0001

Data Index: 1493558 (Python Code)

Max Activating Token Index: 643

Text #11

Max Range: 0.6195. Min Range: -0.6195

Max Act: 0.4668. Min Act: -0.0001

Data Index: 1542668 (Python Code)

Max Activating Token Index: 280

Text #12

Max Range: 0.6195. Min Range: -0.6195

Max Act: 0.4712. Min Act: -0.0001

Data Index: 1360204 (Python Code)

Max Activating Token Index: 480

Text #13

Max Range: 0.6195. Min Range: -0.6195

Max Act: 0.4783. Min Act: -0.0001

Data Index: 1452363 (Python Code)

Max Activating Token Index: 206

Text #14

Max Range: 0.6195. Min Range: -0.6195

Max Act: 0.4457. Min Act: -0.0001

Data Index: 1544979 (Python Code)

Max Activating Token Index: 780

Text #15

Max Range: 0.6195. Min Range: -0.6195

Max Act: 0.4764. Min Act: -0.0001

Data Index: 1427149 (Python Code)

Max Activating Token Index: 946

Text #16

Max Range: 0.6195. Min Range: -0.6195

Max Act: 0.4576. Min Act: -0.0001

Data Index: 1387976 (Python Code)

Max Activating Token Index: 260

Text #17

Max Range: 0.6195. Min Range: -0.6195

Max Act: 0.4530. Min Act: -0.0001

Data Index: 1486626 (Python Code)

Max Activating Token Index: 106

Text #18

Max Range: 0.6195. Min Range: -0.6195

Max Act: 0.4637. Min Act: -0.0001

Data Index: 1498068 (Python Code)

Max Activating Token Index: 466

Text #19

Max Range: 0.6195. Min Range: -0.6195

Max Act: 0.4457. Min Act: -0.0001

Data Index: 1416576 (Python Code)

Max Activating Token Index: 477