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

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

Neuron 4389 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: 0.5207. Min Range: -0.5207

Max Act: 0.5207. Min Act: -0.0000

Data Index: 1571371 (Python Code)

Max Activating Token Index: 666

Text #1

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.5105. Min Act: -0.0000

Data Index: 1420170 (Python Code)

Max Activating Token Index: 416

Text #2

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.4305. Min Act: -0.0000

Data Index: 1638644 (Python Code)

Max Activating Token Index: 320

Text #3

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.3880. Min Act: -0.0000

Data Index: 1634357 (Python Code)

Max Activating Token Index: 133

Text #4

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.3960. Min Act: -0.0000

Data Index: 1543158 (Python Code)

Max Activating Token Index: 496

Text #5

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.3680. Min Act: -0.0000

Data Index: 1610521 (Python Code)

Max Activating Token Index: 600

Text #6

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.3183. Min Act: -0.0000

Data Index: 1444244 (Python Code)

Max Activating Token Index: 43

Text #7

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.3259. Min Act: -0.0000

Data Index: 1475068 (Python Code)

Max Activating Token Index: 119

Text #8

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.3230. Min Act: -0.0000

Data Index: 1636974 (Python Code)

Max Activating Token Index: 71

Text #9

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.3017. Min Act: -0.0000

Data Index: 1541388 (Python Code)

Max Activating Token Index: 248

Text #10

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.3317. Min Act: -0.0000

Data Index: 1486925 (Python Code)

Max Activating Token Index: 103

Text #11

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.3198. Min Act: -0.0000

Data Index: 1511561 (Python Code)

Max Activating Token Index: 41

Text #12

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.3213. Min Act: -0.0000

Data Index: 1600103 (Python Code)

Max Activating Token Index: 800

Text #13

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.3098. Min Act: -0.0000

Data Index: 1579087 (Python Code)

Max Activating Token Index: 191

Text #14

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.2973. Min Act: -0.0000

Data Index: 1505259 (Python Code)

Max Activating Token Index: 285

Text #15

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.2976. Min Act: -0.0000

Data Index: 1578008 (Python Code)

Max Activating Token Index: 449

Text #16

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.2919. Min Act: -0.0000

Data Index: 1399686 (Python Code)

Max Activating Token Index: 438

Text #17

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.3039. Min Act: -0.0000

Data Index: 1377534 (Python Code)

Max Activating Token Index: 114

Text #18

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.2992. Min Act: -0.0000

Data Index: 1569655 (Python Code)

Max Activating Token Index: 229

Text #19

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.2931. Min Act: -0.0000

Data Index: 1543282 (Python Code)

Max Activating Token Index: 378