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

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

Neuron 4350 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8565. Min Range: -0.8565

Max Act: 0.8565. Min Act: 0.0000

Data Index: 1451520 (Python Code)

Max Activating Token Index: 792

Text #1

Max Range: 0.8565. Min Range: -0.8565

Max Act: 0.6978. Min Act: -0.0000

Data Index: 1388604 (Python Code)

Max Activating Token Index: 96

Text #2

Max Range: 0.8565. Min Range: -0.8565

Max Act: 0.6120. Min Act: -0.0000

Data Index: 1496185 (Python Code)

Max Activating Token Index: 654

Text #3

Max Range: 0.8565. Min Range: -0.8565

Max Act: 0.5644. Min Act: -0.0000

Data Index: 723161 (C4 (Web Text))

Max Activating Token Index: 206

Text #4

Max Range: 0.8565. Min Range: -0.8565

Max Act: 0.5365. Min Act: -0.0000

Data Index: 1441201 (Python Code)

Max Activating Token Index: 359

Text #5

Max Range: 0.8565. Min Range: -0.8565

Max Act: 0.5539. Min Act: 0.0000

Data Index: 1360839 (Python Code)

Max Activating Token Index: 235

Text #6

Max Range: 0.8565. Min Range: -0.8565

Max Act: 0.5160. Min Act: -0.0000

Data Index: 77850 (C4 (Web Text))

Max Activating Token Index: 195

Text #7

Max Range: 0.8565. Min Range: -0.8565

Max Act: 0.5183. Min Act: -0.0000

Data Index: 1115761 (C4 (Web Text))

Max Activating Token Index: 87

Text #8

Max Range: 0.8565. Min Range: -0.8565

Max Act: 0.5291. Min Act: -0.0000

Data Index: 1482122 (Python Code)

Max Activating Token Index: 408

Text #9

Max Range: 0.8565. Min Range: -0.8565

Max Act: 0.5319. Min Act: 0.0000

Data Index: 1481098 (Python Code)

Max Activating Token Index: 978

Text #10

Max Range: 0.8565. Min Range: -0.8565

Max Act: 0.5324. Min Act: -0.0000

Data Index: 1387294 (Python Code)

Max Activating Token Index: 797

Text #11

Max Range: 0.8565. Min Range: -0.8565

Max Act: 0.5243. Min Act: -0.0000

Data Index: 1554557 (Python Code)

Max Activating Token Index: 124

Text #12

Max Range: 0.8565. Min Range: -0.8565

Max Act: 0.5148. Min Act: -0.0000

Data Index: 1411482 (Python Code)

Max Activating Token Index: 953

Text #13

Max Range: 0.8565. Min Range: -0.8565

Max Act: 0.5344. Min Act: -0.0000

Data Index: 962449 (C4 (Web Text))

Max Activating Token Index: 119

Text #14

Max Range: 0.8565. Min Range: -0.8565

Max Act: 0.5195. Min Act: -0.0000

Data Index: 1537055 (Python Code)

Max Activating Token Index: 164

Text #15

Max Range: 0.8565. Min Range: -0.8565

Max Act: 0.5329. Min Act: 0.0000

Data Index: 1579252 (Python Code)

Max Activating Token Index: 366

Text #16

Max Range: 0.8565. Min Range: -0.8565

Max Act: 0.4809. Min Act: -0.0000

Data Index: 1402000 (Python Code)

Max Activating Token Index: 442

Text #17

Max Range: 0.8565. Min Range: -0.8565

Max Act: 0.4856. Min Act: -0.0000

Data Index: 1318218 (C4 (Web Text))

Max Activating Token Index: 116

Text #18

Max Range: 0.8565. Min Range: -0.8565

Max Act: 0.5014. Min Act: 0.0000

Data Index: 1652372 (Python Code)

Max Activating Token Index: 186

Text #19

Max Range: 0.8565. Min Range: -0.8565

Max Act: 0.5071. Min Act: -0.0000

Data Index: 1494333 (Python Code)

Max Activating Token Index: 545