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

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

Neuron 3954 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7099. Min Range: -1.7099

Max Act: 1.7099. Min Act: -0.0001

Data Index: 837732 (C4 (Web Text))

Max Activating Token Index: 201

Text #1

Max Range: 1.7099. Min Range: -1.7099

Max Act: 1.6487. Min Act: -0.0001

Data Index: 410864 (C4 (Web Text))

Max Activating Token Index: 900

Text #2

Max Range: 1.7099. Min Range: -1.7099

Max Act: 1.5963. Min Act: -0.0001

Data Index: 444488 (C4 (Web Text))

Max Activating Token Index: 21

Text #3

Max Range: 1.7099. Min Range: -1.7099

Max Act: 1.3889. Min Act: -0.0001

Data Index: 336826 (C4 (Web Text))

Max Activating Token Index: 489

Text #4

Max Range: 1.7099. Min Range: -1.7099

Max Act: 1.3284. Min Act: -0.0001

Data Index: 1199469 (C4 (Web Text))

Max Activating Token Index: 731

Text #5

Max Range: 1.7099. Min Range: -1.7099

Max Act: 1.2495. Min Act: -0.0001

Data Index: 1186756 (C4 (Web Text))

Max Activating Token Index: 689

Text #6

Max Range: 1.7099. Min Range: -1.7099

Max Act: 1.4686. Min Act: -0.0001

Data Index: 1027176 (C4 (Web Text))

Max Activating Token Index: 681

Text #7

Max Range: 1.7099. Min Range: -1.7099

Max Act: 1.3188. Min Act: -0.0001

Data Index: 57083 (C4 (Web Text))

Max Activating Token Index: 245

Text #8

Max Range: 1.7099. Min Range: -1.7099

Max Act: 1.3076. Min Act: -0.0001

Data Index: 214240 (C4 (Web Text))

Max Activating Token Index: 719

Text #9

Max Range: 1.7099. Min Range: -1.7099

Max Act: 1.3713. Min Act: -0.0001

Data Index: 1045365 (C4 (Web Text))

Max Activating Token Index: 155

Text #10

Max Range: 1.7099. Min Range: -1.7099

Max Act: 1.2641. Min Act: -0.0001

Data Index: 941961 (C4 (Web Text))

Max Activating Token Index: 736

Text #11

Max Range: 1.7099. Min Range: -1.7099

Max Act: 1.1664. Min Act: -0.0001

Data Index: 763260 (C4 (Web Text))

Max Activating Token Index: 600

Text #12

Max Range: 1.7099. Min Range: -1.7099

Max Act: 1.2147. Min Act: -0.0001

Data Index: 886346 (C4 (Web Text))

Max Activating Token Index: 895

Text #13

Max Range: 1.7099. Min Range: -1.7099

Max Act: 1.2045. Min Act: -0.0001

Data Index: 1073332 (C4 (Web Text))

Max Activating Token Index: 231

Text #14

Max Range: 1.7099. Min Range: -1.7099

Max Act: 1.2625. Min Act: -0.0001

Data Index: 354727 (C4 (Web Text))

Max Activating Token Index: 363

Text #15

Max Range: 1.7099. Min Range: -1.7099

Max Act: 1.1947. Min Act: -0.0001

Data Index: 895543 (C4 (Web Text))

Max Activating Token Index: 507

Text #16

Max Range: 1.7099. Min Range: -1.7099

Max Act: 1.2693. Min Act: -0.0001

Data Index: 801665 (C4 (Web Text))

Max Activating Token Index: 223

Text #17

Max Range: 1.7099. Min Range: -1.7099

Max Act: 1.1827. Min Act: -0.0001

Data Index: 357174 (C4 (Web Text))

Max Activating Token Index: 262

Text #18

Max Range: 1.7099. Min Range: -1.7099

Max Act: 1.1545. Min Act: -0.0001

Data Index: 892576 (C4 (Web Text))

Max Activating Token Index: 113

Text #19

Max Range: 1.7099. Min Range: -1.7099

Max Act: 1.1861. Min Act: -0.0001

Data Index: 374736 (C4 (Web Text))

Max Activating Token Index: 167