Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4159 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3531. Min Range: -1.3531

Max Act: 1.3531. Min Act: -0.0000

Data Index: 1250527 (C4 (Web Text))

Max Activating Token Index: 999

Text #1

Max Range: 1.3531. Min Range: -1.3531

Max Act: 1.1228. Min Act: -0.0000

Data Index: 1121048 (C4 (Web Text))

Max Activating Token Index: 892

Text #2

Max Range: 1.3531. Min Range: -1.3531

Max Act: 0.8059. Min Act: -0.0000

Data Index: 1138991 (C4 (Web Text))

Max Activating Token Index: 116

Text #3

Max Range: 1.3531. Min Range: -1.3531

Max Act: 0.8327. Min Act: -0.0000

Data Index: 633759 (C4 (Web Text))

Max Activating Token Index: 589

Text #4

Max Range: 1.3531. Min Range: -1.3531

Max Act: 0.7467. Min Act: -0.0000

Data Index: 749092 (C4 (Web Text))

Max Activating Token Index: 333

Text #5

Max Range: 1.3531. Min Range: -1.3531

Max Act: 0.7434. Min Act: -0.0000

Data Index: 390423 (C4 (Web Text))

Max Activating Token Index: 44

Text #6

Max Range: 1.3531. Min Range: -1.3531

Max Act: 0.7315. Min Act: -0.0000

Data Index: 993312 (C4 (Web Text))

Max Activating Token Index: 519

Text #7

Max Range: 1.3531. Min Range: -1.3531

Max Act: 0.6982. Min Act: -0.0000

Data Index: 621087 (C4 (Web Text))

Max Activating Token Index: 298

Text #8

Max Range: 1.3531. Min Range: -1.3531

Max Act: 0.6851. Min Act: -0.0000

Data Index: 509965 (C4 (Web Text))

Max Activating Token Index: 953

Text #9

Max Range: 1.3531. Min Range: -1.3531

Max Act: 0.6674. Min Act: -0.0000

Data Index: 401393 (C4 (Web Text))

Max Activating Token Index: 224

Text #10

Max Range: 1.3531. Min Range: -1.3531

Max Act: 0.6810. Min Act: -0.0000

Data Index: 1024149 (C4 (Web Text))

Max Activating Token Index: 60

Text #11

Max Range: 1.3531. Min Range: -1.3531

Max Act: 0.6726. Min Act: -0.0000

Data Index: 721192 (C4 (Web Text))

Max Activating Token Index: 818

Text #12

Max Range: 1.3531. Min Range: -1.3531

Max Act: 0.7166. Min Act: -0.0000

Data Index: 460365 (C4 (Web Text))

Max Activating Token Index: 569

Text #13

Max Range: 1.3531. Min Range: -1.3531

Max Act: 0.6413. Min Act: -0.0000

Data Index: 510723 (C4 (Web Text))

Max Activating Token Index: 914

Text #14

Max Range: 1.3531. Min Range: -1.3531

Max Act: 0.6943. Min Act: -0.0000

Data Index: 148650 (C4 (Web Text))

Max Activating Token Index: 129

Text #15

Max Range: 1.3531. Min Range: -1.3531

Max Act: 0.6070. Min Act: -0.0000

Data Index: 1186843 (C4 (Web Text))

Max Activating Token Index: 128

Text #16

Max Range: 1.3531. Min Range: -1.3531

Max Act: 0.6286. Min Act: -0.0000

Data Index: 399574 (C4 (Web Text))

Max Activating Token Index: 908

Text #17

Max Range: 1.3531. Min Range: -1.3531

Max Act: 0.6422. Min Act: -0.0000

Data Index: 1357462 (C4 (Web Text))

Max Activating Token Index: 62

Text #18

Max Range: 1.3531. Min Range: -1.3531

Max Act: 0.6212. Min Act: -0.0000

Data Index: 1168717 (C4 (Web Text))

Max Activating Token Index: 987

Text #19

Max Range: 1.3531. Min Range: -1.3531

Max Act: 0.5928. Min Act: -0.0000

Data Index: 1167501 (C4 (Web Text))

Max Activating Token Index: 895