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

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

Neuron 3023 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8482. Min Range: -2.8482

Max Act: 2.8482. Min Act: -0.0000

Data Index: 648859 (C4 (Web Text))

Max Activating Token Index: 803

Text #1

Max Range: 2.8482. Min Range: -2.8482

Max Act: 2.2896. Min Act: -0.0000

Data Index: 41234 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 2.8482. Min Range: -2.8482

Max Act: 2.2736. Min Act: -0.0000

Data Index: 1008184 (C4 (Web Text))

Max Activating Token Index: 855

Text #3

Max Range: 2.8482. Min Range: -2.8482

Max Act: 2.1651. Min Act: -0.0000

Data Index: 784477 (C4 (Web Text))

Max Activating Token Index: 771

Text #4

Max Range: 2.8482. Min Range: -2.8482

Max Act: 1.9652. Min Act: -0.0000

Data Index: 637636 (C4 (Web Text))

Max Activating Token Index: 717

Text #5

Max Range: 2.8482. Min Range: -2.8482

Max Act: 1.9343. Min Act: -0.0000

Data Index: 270881 (C4 (Web Text))

Max Activating Token Index: 529

Text #6

Max Range: 2.8482. Min Range: -2.8482

Max Act: 2.0137. Min Act: -0.0000

Data Index: 667947 (C4 (Web Text))

Max Activating Token Index: 334

Text #7

Max Range: 2.8482. Min Range: -2.8482

Max Act: 1.8854. Min Act: -0.0000

Data Index: 598511 (C4 (Web Text))

Max Activating Token Index: 1013

Text #8

Max Range: 2.8482. Min Range: -2.8482

Max Act: 1.8261. Min Act: -0.0000

Data Index: 1344116 (C4 (Web Text))

Max Activating Token Index: 13

Text #9

Max Range: 2.8482. Min Range: -2.8482

Max Act: 1.8123. Min Act: -0.0000

Data Index: 155896 (C4 (Web Text))

Max Activating Token Index: 1019

Text #10

Max Range: 2.8482. Min Range: -2.8482

Max Act: 1.7105. Min Act: -0.0000

Data Index: 661204 (C4 (Web Text))

Max Activating Token Index: 285

Text #11

Max Range: 2.8482. Min Range: -2.8482

Max Act: 1.7845. Min Act: -0.0000

Data Index: 252174 (C4 (Web Text))

Max Activating Token Index: 456

Text #12

Max Range: 2.8482. Min Range: -2.8482

Max Act: 1.6830. Min Act: -0.0000

Data Index: 835819 (C4 (Web Text))

Max Activating Token Index: 999

Text #13

Max Range: 2.8482. Min Range: -2.8482

Max Act: 1.5622. Min Act: -0.0000

Data Index: 260242 (C4 (Web Text))

Max Activating Token Index: 400

Text #14

Max Range: 2.8482. Min Range: -2.8482

Max Act: 1.7410. Min Act: -0.0000

Data Index: 528215 (C4 (Web Text))

Max Activating Token Index: 993

Text #15

Max Range: 2.8482. Min Range: -2.8482

Max Act: 1.6389. Min Act: -0.0000

Data Index: 1204082 (C4 (Web Text))

Max Activating Token Index: 862

Text #16

Max Range: 2.8482. Min Range: -2.8482

Max Act: 1.7160. Min Act: -0.0000

Data Index: 149367 (C4 (Web Text))

Max Activating Token Index: 653

Text #17

Max Range: 2.8482. Min Range: -2.8482

Max Act: 1.8153. Min Act: -0.0000

Data Index: 262236 (C4 (Web Text))

Max Activating Token Index: 69

Text #18

Max Range: 2.8482. Min Range: -2.8482

Max Act: 1.6037. Min Act: -0.0000

Data Index: 691497 (C4 (Web Text))

Max Activating Token Index: 136

Text #19

Max Range: 2.8482. Min Range: -2.8482

Max Act: 1.7585. Min Act: -0.0000

Data Index: 934539 (C4 (Web Text))

Max Activating Token Index: 252