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

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

Neuron 2585 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.2430. Min Range: -6.2430

Max Act: 6.1937. Min Act: -0.0000

Data Index: 698735 (C4 (Web Text))

Max Activating Token Index: 340

Text #1

Max Range: 6.2430. Min Range: -6.2430

Max Act: 5.9462. Min Act: -0.0000

Data Index: 589159 (C4 (Web Text))

Max Activating Token Index: 318

Text #2

Max Range: 6.2430. Min Range: -6.2430

Max Act: 6.2430. Min Act: -0.0000

Data Index: 175996 (C4 (Web Text))

Max Activating Token Index: 142

Text #3

Max Range: 6.2430. Min Range: -6.2430

Max Act: 5.8076. Min Act: -0.0000

Data Index: 236257 (C4 (Web Text))

Max Activating Token Index: 509

Text #4

Max Range: 6.2430. Min Range: -6.2430

Max Act: 5.7741. Min Act: -0.0000

Data Index: 1279726 (C4 (Web Text))

Max Activating Token Index: 523

Text #5

Max Range: 6.2430. Min Range: -6.2430

Max Act: 5.4421. Min Act: -0.0000

Data Index: 810944 (C4 (Web Text))

Max Activating Token Index: 861

Text #6

Max Range: 6.2430. Min Range: -6.2430

Max Act: 5.6035. Min Act: -0.0000

Data Index: 606926 (C4 (Web Text))

Max Activating Token Index: 806

Text #7

Max Range: 6.2430. Min Range: -6.2430

Max Act: 5.1582. Min Act: -0.0000

Data Index: 762102 (C4 (Web Text))

Max Activating Token Index: 27

Text #8

Max Range: 6.2430. Min Range: -6.2430

Max Act: 3.9228. Min Act: -0.0000

Data Index: 1133422 (C4 (Web Text))

Max Activating Token Index: 424

Text #9

Max Range: 6.2430. Min Range: -6.2430

Max Act: 4.0946. Min Act: -0.0000

Data Index: 351506 (C4 (Web Text))

Max Activating Token Index: 37

Text #10

Max Range: 6.2430. Min Range: -6.2430

Max Act: 3.8005. Min Act: -0.0000

Data Index: 439133 (C4 (Web Text))

Max Activating Token Index: 679

Text #11

Max Range: 6.2430. Min Range: -6.2430

Max Act: 3.8337. Min Act: -0.0000

Data Index: 13724 (C4 (Web Text))

Max Activating Token Index: 406

Text #12

Max Range: 6.2430. Min Range: -6.2430

Max Act: 3.6469. Min Act: -0.0000

Data Index: 249069 (C4 (Web Text))

Max Activating Token Index: 553

Text #13

Max Range: 6.2430. Min Range: -6.2430

Max Act: 3.5675. Min Act: -0.0000

Data Index: 673321 (C4 (Web Text))

Max Activating Token Index: 534

Text #14

Max Range: 6.2430. Min Range: -6.2430

Max Act: 3.5683. Min Act: -0.0000

Data Index: 1152632 (C4 (Web Text))

Max Activating Token Index: 163

Text #15

Max Range: 6.2430. Min Range: -6.2430

Max Act: 3.5193. Min Act: -0.0000

Data Index: 1284051 (C4 (Web Text))

Max Activating Token Index: 833

Text #16

Max Range: 6.2430. Min Range: -6.2430

Max Act: 3.3087. Min Act: -0.0000

Data Index: 154112 (C4 (Web Text))

Max Activating Token Index: 434

Text #17

Max Range: 6.2430. Min Range: -6.2430

Max Act: 3.4389. Min Act: -0.0000

Data Index: 162558 (C4 (Web Text))

Max Activating Token Index: 473

Text #18

Max Range: 6.2430. Min Range: -6.2430

Max Act: 3.7040. Min Act: -0.0000

Data Index: 846264 (C4 (Web Text))

Max Activating Token Index: 738

Text #19

Max Range: 6.2430. Min Range: -6.2430

Max Act: 3.4078. Min Act: -0.0000

Data Index: 244947 (C4 (Web Text))

Max Activating Token Index: 404