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

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

Neuron 2584 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 2.3193. Min Range: -2.3193

Max Act: 2.3193. Min Act: -0.0002

Data Index: 975121 (C4 (Web Text))

Max Activating Token Index: 828

Text #1

Max Range: 2.3193. Min Range: -2.3193

Max Act: 2.2831. Min Act: -0.0002

Data Index: 385864 (C4 (Web Text))

Max Activating Token Index: 806

Text #2

Max Range: 2.3193. Min Range: -2.3193

Max Act: 2.1888. Min Act: -0.0002

Data Index: 1120821 (C4 (Web Text))

Max Activating Token Index: 1009

Text #3

Max Range: 2.3193. Min Range: -2.3193

Max Act: 2.2240. Min Act: -0.0002

Data Index: 914498 (C4 (Web Text))

Max Activating Token Index: 908

Text #4

Max Range: 2.3193. Min Range: -2.3193

Max Act: 2.1292. Min Act: -0.0002

Data Index: 1262669 (C4 (Web Text))

Max Activating Token Index: 899

Text #5

Max Range: 2.3193. Min Range: -2.3193

Max Act: 2.1079. Min Act: -0.0002

Data Index: 38312 (C4 (Web Text))

Max Activating Token Index: 681

Text #6

Max Range: 2.3193. Min Range: -2.3193

Max Act: 2.1263. Min Act: -0.0002

Data Index: 233089 (C4 (Web Text))

Max Activating Token Index: 814

Text #7

Max Range: 2.3193. Min Range: -2.3193

Max Act: 2.0954. Min Act: -0.0002

Data Index: 814450 (C4 (Web Text))

Max Activating Token Index: 548

Text #8

Max Range: 2.3193. Min Range: -2.3193

Max Act: 2.0986. Min Act: -0.0002

Data Index: 276157 (C4 (Web Text))

Max Activating Token Index: 944

Text #9

Max Range: 2.3193. Min Range: -2.3193

Max Act: 2.0105. Min Act: -0.0002

Data Index: 293287 (C4 (Web Text))

Max Activating Token Index: 801

Text #10

Max Range: 2.3193. Min Range: -2.3193

Max Act: 2.0013. Min Act: -0.0002

Data Index: 392090 (C4 (Web Text))

Max Activating Token Index: 440

Text #11

Max Range: 2.3193. Min Range: -2.3193

Max Act: 1.9667. Min Act: -0.0002

Data Index: 779997 (C4 (Web Text))

Max Activating Token Index: 435

Text #12

Max Range: 2.3193. Min Range: -2.3193

Max Act: 2.0786. Min Act: -0.0002

Data Index: 264436 (C4 (Web Text))

Max Activating Token Index: 852

Text #13

Max Range: 2.3193. Min Range: -2.3193

Max Act: 2.0151. Min Act: -0.0002

Data Index: 433052 (C4 (Web Text))

Max Activating Token Index: 423

Text #14

Max Range: 2.3193. Min Range: -2.3193

Max Act: 1.9474. Min Act: -0.0002

Data Index: 1060678 (C4 (Web Text))

Max Activating Token Index: 417

Text #15

Max Range: 2.3193. Min Range: -2.3193

Max Act: 1.8941. Min Act: -0.0002

Data Index: 115702 (C4 (Web Text))

Max Activating Token Index: 941

Text #16

Max Range: 2.3193. Min Range: -2.3193

Max Act: 1.8934. Min Act: -0.0002

Data Index: 1142851 (C4 (Web Text))

Max Activating Token Index: 22

Text #17

Max Range: 2.3193. Min Range: -2.3193

Max Act: 1.8597. Min Act: -0.0002

Data Index: 936679 (C4 (Web Text))

Max Activating Token Index: 932

Text #18

Max Range: 2.3193. Min Range: -2.3193

Max Act: 1.8813. Min Act: -0.0002

Data Index: 616334 (C4 (Web Text))

Max Activating Token Index: 797

Text #19

Max Range: 2.3193. Min Range: -2.3193

Max Act: 1.9497. Min Act: -0.0002

Data Index: 892630 (C4 (Web Text))

Max Activating Token Index: 539