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

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

Neuron 759 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: 2.7054. Min Range: -2.7054

Max Act: 2.6132. Min Act: -0.0001

Data Index: 1411047 (Python Code)

Max Activating Token Index: 61

Text #1

Max Range: 2.7054. Min Range: -2.7054

Max Act: 2.5794. Min Act: -0.0001

Data Index: 1589683 (Python Code)

Max Activating Token Index: 269

Text #2

Max Range: 2.7054. Min Range: -2.7054

Max Act: 2.7054. Min Act: -0.0001

Data Index: 1543186 (Python Code)

Max Activating Token Index: 187

Text #3

Max Range: 2.7054. Min Range: -2.7054

Max Act: 2.4153. Min Act: -0.0001

Data Index: 1619864 (Python Code)

Max Activating Token Index: 43

Text #4

Max Range: 2.7054. Min Range: -2.7054

Max Act: 2.3194. Min Act: -0.0001

Data Index: 1527448 (Python Code)

Max Activating Token Index: 211

Text #5

Max Range: 2.7054. Min Range: -2.7054

Max Act: 2.5413. Min Act: -0.0001

Data Index: 1602613 (Python Code)

Max Activating Token Index: 169

Text #6

Max Range: 2.7054. Min Range: -2.7054

Max Act: 2.3940. Min Act: -0.0001

Data Index: 1435532 (Python Code)

Max Activating Token Index: 622

Text #7

Max Range: 2.7054. Min Range: -2.7054

Max Act: 2.3752. Min Act: -0.0001

Data Index: 1637915 (Python Code)

Max Activating Token Index: 494

Text #8

Max Range: 2.7054. Min Range: -2.7054

Max Act: 2.4555. Min Act: -0.0001

Data Index: 1408963 (Python Code)

Max Activating Token Index: 208

Text #9

Max Range: 2.7054. Min Range: -2.7054

Max Act: 2.4219. Min Act: -0.0001

Data Index: 1544831 (Python Code)

Max Activating Token Index: 93

Text #10

Max Range: 2.7054. Min Range: -2.7054

Max Act: 2.2729. Min Act: -0.0001

Data Index: 1396230 (Python Code)

Max Activating Token Index: 145

Text #11

Max Range: 2.7054. Min Range: -2.7054

Max Act: 2.2616. Min Act: -0.0001

Data Index: 1505398 (Python Code)

Max Activating Token Index: 287

Text #12

Max Range: 2.7054. Min Range: -2.7054

Max Act: 2.3158. Min Act: -0.0001

Data Index: 1472096 (Python Code)

Max Activating Token Index: 170

Text #13

Max Range: 2.7054. Min Range: -2.7054

Max Act: 2.1943. Min Act: -0.0001

Data Index: 1552384 (Python Code)

Max Activating Token Index: 984

Text #14

Max Range: 2.7054. Min Range: -2.7054

Max Act: 2.2260. Min Act: -0.0001

Data Index: 1522257 (Python Code)

Max Activating Token Index: 280

Text #15

Max Range: 2.7054. Min Range: -2.7054

Max Act: 1.9970. Min Act: -0.0001

Data Index: 1510158 (Python Code)

Max Activating Token Index: 696

Text #16

Max Range: 2.7054. Min Range: -2.7054

Max Act: 2.1199. Min Act: -0.0001

Data Index: 1379816 (Python Code)

Max Activating Token Index: 588

Text #17

Max Range: 2.7054. Min Range: -2.7054

Max Act: 2.0845. Min Act: -0.0001

Data Index: 1386697 (Python Code)

Max Activating Token Index: 464

Text #18

Max Range: 2.7054. Min Range: -2.7054

Max Act: 2.0859. Min Act: -0.0001

Data Index: 1539266 (Python Code)

Max Activating Token Index: 966

Text #19

Max Range: 2.7054. Min Range: -2.7054

Max Act: 2.1890. Min Act: -0.0001

Data Index: 1460811 (Python Code)

Max Activating Token Index: 885