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

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

Neuron 3957 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: 1.2649. Min Range: -1.2649

Max Act: 1.2649. Min Act: -0.0000

Data Index: 608926 (C4 (Web Text))

Max Activating Token Index: 835

Text #1

Max Range: 1.2649. Min Range: -1.2649

Max Act: 0.9567. Min Act: -0.0000

Data Index: 1092002 (C4 (Web Text))

Max Activating Token Index: 935

Text #2

Max Range: 1.2649. Min Range: -1.2649

Max Act: 0.9385. Min Act: -0.0000

Data Index: 459444 (C4 (Web Text))

Max Activating Token Index: 267

Text #3

Max Range: 1.2649. Min Range: -1.2649

Max Act: 0.9172. Min Act: -0.0000

Data Index: 944630 (C4 (Web Text))

Max Activating Token Index: 237

Text #4

Max Range: 1.2649. Min Range: -1.2649

Max Act: 0.9140. Min Act: -0.0000

Data Index: 380446 (C4 (Web Text))

Max Activating Token Index: 227

Text #5

Max Range: 1.2649. Min Range: -1.2649

Max Act: 0.8512. Min Act: -0.0000

Data Index: 782115 (C4 (Web Text))

Max Activating Token Index: 99

Text #6

Max Range: 1.2649. Min Range: -1.2649

Max Act: 0.8202. Min Act: -0.0000

Data Index: 384700 (C4 (Web Text))

Max Activating Token Index: 132

Text #7

Max Range: 1.2649. Min Range: -1.2649

Max Act: 0.8860. Min Act: -0.0000

Data Index: 217303 (C4 (Web Text))

Max Activating Token Index: 789

Text #8

Max Range: 1.2649. Min Range: -1.2649

Max Act: 0.8108. Min Act: -0.0000

Data Index: 992247 (C4 (Web Text))

Max Activating Token Index: 1020

Text #9

Max Range: 1.2649. Min Range: -1.2649

Max Act: 0.8084. Min Act: -0.0000

Data Index: 659897 (C4 (Web Text))

Max Activating Token Index: 737

Text #10

Max Range: 1.2649. Min Range: -1.2649

Max Act: 0.8041. Min Act: -0.0000

Data Index: 1078152 (C4 (Web Text))

Max Activating Token Index: 20

Text #11

Max Range: 1.2649. Min Range: -1.2649

Max Act: 0.7813. Min Act: -0.0000

Data Index: 741900 (C4 (Web Text))

Max Activating Token Index: 450

Text #12

Max Range: 1.2649. Min Range: -1.2649

Max Act: 0.7907. Min Act: -0.0000

Data Index: 653029 (C4 (Web Text))

Max Activating Token Index: 100

Text #13

Max Range: 1.2649. Min Range: -1.2649

Max Act: 0.7436. Min Act: -0.0000

Data Index: 1186386 (C4 (Web Text))

Max Activating Token Index: 839

Text #14

Max Range: 1.2649. Min Range: -1.2649

Max Act: 0.7824. Min Act: -0.0000

Data Index: 176250 (C4 (Web Text))

Max Activating Token Index: 344

Text #15

Max Range: 1.2649. Min Range: -1.2649

Max Act: 0.7705. Min Act: -0.0000

Data Index: 114950 (C4 (Web Text))

Max Activating Token Index: 480

Text #16

Max Range: 1.2649. Min Range: -1.2649

Max Act: 0.7400. Min Act: -0.0000

Data Index: 995683 (C4 (Web Text))

Max Activating Token Index: 816

Text #17

Max Range: 1.2649. Min Range: -1.2649

Max Act: 0.7700. Min Act: -0.0000

Data Index: 1355245 (C4 (Web Text))

Max Activating Token Index: 383

Text #18

Max Range: 1.2649. Min Range: -1.2649

Max Act: 0.7819. Min Act: -0.0000

Data Index: 1226851 (C4 (Web Text))

Max Activating Token Index: 773

Text #19

Max Range: 1.2649. Min Range: -1.2649

Max Act: 0.7604. Min Act: -0.0000

Data Index: 770936 (C4 (Web Text))

Max Activating Token Index: 219