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

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

Neuron 984 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.8412. Min Range: -1.8412

Max Act: 1.8412. Min Act: -0.0000

Data Index: 132963 (C4 (Web Text))

Max Activating Token Index: 124

Text #1

Max Range: 1.8412. Min Range: -1.8412

Max Act: 1.6726. Min Act: -0.0000

Data Index: 348803 (C4 (Web Text))

Max Activating Token Index: 850

Text #2

Max Range: 1.8412. Min Range: -1.8412

Max Act: 1.8354. Min Act: -0.0001

Data Index: 51717 (C4 (Web Text))

Max Activating Token Index: 123

Text #3

Max Range: 1.8412. Min Range: -1.8412

Max Act: 1.7093. Min Act: -0.0001

Data Index: 1123324 (C4 (Web Text))

Max Activating Token Index: 384

Text #4

Max Range: 1.8412. Min Range: -1.8412

Max Act: 1.6854. Min Act: -0.0000

Data Index: 1042116 (C4 (Web Text))

Max Activating Token Index: 922

Text #5

Max Range: 1.8412. Min Range: -1.8412

Max Act: 1.6745. Min Act: -0.0000

Data Index: 474856 (C4 (Web Text))

Max Activating Token Index: 70

Text #6

Max Range: 1.8412. Min Range: -1.8412

Max Act: 1.6682. Min Act: -0.0000

Data Index: 791286 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 1.8412. Min Range: -1.8412

Max Act: 1.6939. Min Act: -0.0000

Data Index: 820086 (C4 (Web Text))

Max Activating Token Index: 424

Text #8

Max Range: 1.8412. Min Range: -1.8412

Max Act: 1.5770. Min Act: -0.0001

Data Index: 724014 (C4 (Web Text))

Max Activating Token Index: 423

Text #9

Max Range: 1.8412. Min Range: -1.8412

Max Act: 1.5055. Min Act: -0.0000

Data Index: 427464 (C4 (Web Text))

Max Activating Token Index: 292

Text #10

Max Range: 1.8412. Min Range: -1.8412

Max Act: 1.5154. Min Act: -0.0001

Data Index: 309498 (C4 (Web Text))

Max Activating Token Index: 823

Text #11

Max Range: 1.8412. Min Range: -1.8412

Max Act: 1.5365. Min Act: -0.0001

Data Index: 312135 (C4 (Web Text))

Max Activating Token Index: 69

Text #12

Max Range: 1.8412. Min Range: -1.8412

Max Act: 1.5949. Min Act: -0.0000

Data Index: 1114256 (C4 (Web Text))

Max Activating Token Index: 923

Text #13

Max Range: 1.8412. Min Range: -1.8412

Max Act: 1.5239. Min Act: -0.0001

Data Index: 488547 (C4 (Web Text))

Max Activating Token Index: 22

Text #14

Max Range: 1.8412. Min Range: -1.8412

Max Act: 1.5308. Min Act: -0.0001

Data Index: 798303 (C4 (Web Text))

Max Activating Token Index: 357

Text #15

Max Range: 1.8412. Min Range: -1.8412

Max Act: 1.3745. Min Act: -0.0001

Data Index: 1193470 (C4 (Web Text))

Max Activating Token Index: 102

Text #16

Max Range: 1.8412. Min Range: -1.8412

Max Act: 1.3597. Min Act: -0.0000

Data Index: 617837 (C4 (Web Text))

Max Activating Token Index: 111

Text #17

Max Range: 1.8412. Min Range: -1.8412

Max Act: 1.4817. Min Act: -0.0001

Data Index: 599512 (C4 (Web Text))

Max Activating Token Index: 256

Text #18

Max Range: 1.8412. Min Range: -1.8412

Max Act: 1.4658. Min Act: -0.0000

Data Index: 496576 (C4 (Web Text))

Max Activating Token Index: 93

Text #19

Max Range: 1.8412. Min Range: -1.8412

Max Act: 1.4026. Min Act: -0.0001

Data Index: 710903 (C4 (Web Text))

Max Activating Token Index: 721