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

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

Neuron 904 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: 5.0422. Min Range: -5.0422

Max Act: 5.0422. Min Act: -0.0001

Data Index: 1157928 (C4 (Web Text))

Max Activating Token Index: 317

Text #1

Max Range: 5.0422. Min Range: -5.0422

Max Act: 4.8682. Min Act: -0.0001

Data Index: 279273 (C4 (Web Text))

Max Activating Token Index: 396

Text #2

Max Range: 5.0422. Min Range: -5.0422

Max Act: 4.5198. Min Act: -0.0001

Data Index: 456836 (C4 (Web Text))

Max Activating Token Index: 920

Text #3

Max Range: 5.0422. Min Range: -5.0422

Max Act: 4.5129. Min Act: -0.0001

Data Index: 579096 (C4 (Web Text))

Max Activating Token Index: 897

Text #4

Max Range: 5.0422. Min Range: -5.0422

Max Act: 4.2699. Min Act: -0.0001

Data Index: 718541 (C4 (Web Text))

Max Activating Token Index: 824

Text #5

Max Range: 5.0422. Min Range: -5.0422

Max Act: 4.6539. Min Act: -0.0001

Data Index: 673211 (C4 (Web Text))

Max Activating Token Index: 310

Text #6

Max Range: 5.0422. Min Range: -5.0422

Max Act: 3.5530. Min Act: -0.0001

Data Index: 47419 (C4 (Web Text))

Max Activating Token Index: 730

Text #7

Max Range: 5.0422. Min Range: -5.0422

Max Act: 4.2046. Min Act: -0.0001

Data Index: 1229920 (C4 (Web Text))

Max Activating Token Index: 880

Text #8

Max Range: 5.0422. Min Range: -5.0422

Max Act: 3.9877. Min Act: -0.0001

Data Index: 796623 (C4 (Web Text))

Max Activating Token Index: 712

Text #9

Max Range: 5.0422. Min Range: -5.0422

Max Act: 4.0804. Min Act: -0.0001

Data Index: 277032 (C4 (Web Text))

Max Activating Token Index: 916

Text #10

Max Range: 5.0422. Min Range: -5.0422

Max Act: 4.0760. Min Act: -0.0001

Data Index: 433338 (C4 (Web Text))

Max Activating Token Index: 1021

Text #11

Max Range: 5.0422. Min Range: -5.0422

Max Act: 4.0632. Min Act: -0.0001

Data Index: 247462 (C4 (Web Text))

Max Activating Token Index: 412

Text #12

Max Range: 5.0422. Min Range: -5.0422

Max Act: 3.8673. Min Act: -0.0001

Data Index: 475612 (C4 (Web Text))

Max Activating Token Index: 546

Text #13

Max Range: 5.0422. Min Range: -5.0422

Max Act: 3.3090. Min Act: -0.0001

Data Index: 234991 (C4 (Web Text))

Max Activating Token Index: 526

Text #14

Max Range: 5.0422. Min Range: -5.0422

Max Act: 3.7780. Min Act: -0.0001

Data Index: 977092 (C4 (Web Text))

Max Activating Token Index: 950

Text #15

Max Range: 5.0422. Min Range: -5.0422

Max Act: 3.7926. Min Act: -0.0001

Data Index: 391514 (C4 (Web Text))

Max Activating Token Index: 437

Text #16

Max Range: 5.0422. Min Range: -5.0422

Max Act: 3.9158. Min Act: -0.0001

Data Index: 985671 (C4 (Web Text))

Max Activating Token Index: 23

Text #17

Max Range: 5.0422. Min Range: -5.0422

Max Act: 3.8404. Min Act: -0.0001

Data Index: 687968 (C4 (Web Text))

Max Activating Token Index: 868

Text #18

Max Range: 5.0422. Min Range: -5.0422

Max Act: 3.8205. Min Act: -0.0001

Data Index: 1266722 (C4 (Web Text))

Max Activating Token Index: 298

Text #19

Max Range: 5.0422. Min Range: -5.0422

Max Act: 3.8159. Min Act: -0.0001

Data Index: 511885 (C4 (Web Text))

Max Activating Token Index: 462