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

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

Neuron 5096 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: 2.7957. Min Range: -2.7957

Max Act: 2.7957. Min Act: -0.0000

Data Index: 976777 (C4 (Web Text))

Max Activating Token Index: 298

Text #1

Max Range: 2.7957. Min Range: -2.7957

Max Act: 2.5163. Min Act: -0.0000

Data Index: 927649 (C4 (Web Text))

Max Activating Token Index: 349

Text #2

Max Range: 2.7957. Min Range: -2.7957

Max Act: 2.6325. Min Act: -0.0000

Data Index: 847390 (C4 (Web Text))

Max Activating Token Index: 230

Text #3

Max Range: 2.7957. Min Range: -2.7957

Max Act: 2.4899. Min Act: -0.0000

Data Index: 845834 (C4 (Web Text))

Max Activating Token Index: 856

Text #4

Max Range: 2.7957. Min Range: -2.7957

Max Act: 2.4132. Min Act: -0.0000

Data Index: 977064 (C4 (Web Text))

Max Activating Token Index: 755

Text #5

Max Range: 2.7957. Min Range: -2.7957

Max Act: 2.2291. Min Act: -0.0000

Data Index: 724984 (C4 (Web Text))

Max Activating Token Index: 948

Text #6

Max Range: 2.7957. Min Range: -2.7957

Max Act: 2.3079. Min Act: -0.0000

Data Index: 68200 (C4 (Web Text))

Max Activating Token Index: 681

Text #7

Max Range: 2.7957. Min Range: -2.7957

Max Act: 2.4050. Min Act: -0.0000

Data Index: 501107 (C4 (Web Text))

Max Activating Token Index: 243

Text #8

Max Range: 2.7957. Min Range: -2.7957

Max Act: 2.1842. Min Act: -0.0000

Data Index: 391709 (C4 (Web Text))

Max Activating Token Index: 196

Text #9

Max Range: 2.7957. Min Range: -2.7957

Max Act: 2.1537. Min Act: -0.0000

Data Index: 951110 (C4 (Web Text))

Max Activating Token Index: 831

Text #10

Max Range: 2.7957. Min Range: -2.7957

Max Act: 2.2848. Min Act: -0.0000

Data Index: 388107 (C4 (Web Text))

Max Activating Token Index: 307

Text #11

Max Range: 2.7957. Min Range: -2.7957

Max Act: 2.3986. Min Act: -0.0000

Data Index: 988739 (C4 (Web Text))

Max Activating Token Index: 864

Text #12

Max Range: 2.7957. Min Range: -2.7957

Max Act: 2.2711. Min Act: -0.0000

Data Index: 662237 (C4 (Web Text))

Max Activating Token Index: 838

Text #13

Max Range: 2.7957. Min Range: -2.7957

Max Act: 2.2451. Min Act: -0.0000

Data Index: 303315 (C4 (Web Text))

Max Activating Token Index: 221

Text #14

Max Range: 2.7957. Min Range: -2.7957

Max Act: 2.0876. Min Act: -0.0000

Data Index: 323268 (C4 (Web Text))

Max Activating Token Index: 799

Text #15

Max Range: 2.7957. Min Range: -2.7957

Max Act: 2.1995. Min Act: -0.0000

Data Index: 846754 (C4 (Web Text))

Max Activating Token Index: 475

Text #16

Max Range: 2.7957. Min Range: -2.7957

Max Act: 2.2740. Min Act: -0.0000

Data Index: 393580 (C4 (Web Text))

Max Activating Token Index: 832

Text #17

Max Range: 2.7957. Min Range: -2.7957

Max Act: 2.0376. Min Act: -0.0000

Data Index: 87058 (C4 (Web Text))

Max Activating Token Index: 626

Text #18

Max Range: 2.7957. Min Range: -2.7957

Max Act: 2.0818. Min Act: -0.0000

Data Index: 588755 (C4 (Web Text))

Max Activating Token Index: 246

Text #19

Max Range: 2.7957. Min Range: -2.7957

Max Act: 1.9571. Min Act: -0.0000

Data Index: 951819 (C4 (Web Text))

Max Activating Token Index: 780