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

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

Neuron 2937 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.8810. Min Act: -0.0001

Data Index: 240241 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.9469. Min Act: -0.0001

Data Index: 12085 (C4 (Web Text))

Max Activating Token Index: 617

Text #2

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.9088. Min Act: -0.0001

Data Index: 1061046 (C4 (Web Text))

Max Activating Token Index: 841

Text #3

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.8834. Min Act: -0.0001

Data Index: 382092 (C4 (Web Text))

Max Activating Token Index: 190

Text #4

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.8083. Min Act: -0.0001

Data Index: 1286568 (C4 (Web Text))

Max Activating Token Index: 725

Text #5

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.8451. Min Act: -0.0001

Data Index: 786809 (C4 (Web Text))

Max Activating Token Index: 699

Text #6

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.8894. Min Act: -0.0001

Data Index: 465660 (C4 (Web Text))

Max Activating Token Index: 251

Text #7

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.7971. Min Act: -0.0001

Data Index: 128572 (C4 (Web Text))

Max Activating Token Index: 874

Text #8

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.8108. Min Act: -0.0001

Data Index: 981801 (C4 (Web Text))

Max Activating Token Index: 978

Text #9

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.8067. Min Act: -0.0001

Data Index: 609839 (C4 (Web Text))

Max Activating Token Index: 563

Text #10

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.7747. Min Act: -0.0002

Data Index: 1266224 (C4 (Web Text))

Max Activating Token Index: 87

Text #11

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.6630. Min Act: -0.0002

Data Index: 1248321 (C4 (Web Text))

Max Activating Token Index: 369

Text #12

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.8226. Min Act: -0.0001

Data Index: 957379 (C4 (Web Text))

Max Activating Token Index: 1021

Text #13

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.7268. Min Act: -0.0001

Data Index: 115446 (C4 (Web Text))

Max Activating Token Index: 857

Text #14

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.7457. Min Act: -0.0001

Data Index: 93811 (C4 (Web Text))

Max Activating Token Index: 132

Text #15

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.7840. Min Act: -0.0001

Data Index: 496338 (C4 (Web Text))

Max Activating Token Index: 566

Text #16

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.7706. Min Act: -0.0001

Data Index: 1030276 (C4 (Web Text))

Max Activating Token Index: 186

Text #17

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.8253. Min Act: -0.0001

Data Index: 80930 (C4 (Web Text))

Max Activating Token Index: 22

Text #18

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.7144. Min Act: -0.0001

Data Index: 1167089 (C4 (Web Text))

Max Activating Token Index: 185

Text #19

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.7749. Min Act: -0.0001

Data Index: 716048 (C4 (Web Text))

Max Activating Token Index: 155