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

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

Neuron 4382 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: 2.0127. Min Range: -2.0127

Max Act: 2.0127. Min Act: -0.0000

Data Index: 709348 (C4 (Web Text))

Max Activating Token Index: 298

Text #1

Max Range: 2.0127. Min Range: -2.0127

Max Act: 1.9107. Min Act: -0.0000

Data Index: 500539 (C4 (Web Text))

Max Activating Token Index: 163

Text #2

Max Range: 2.0127. Min Range: -2.0127

Max Act: 2.0102. Min Act: -0.0000

Data Index: 201935 (C4 (Web Text))

Max Activating Token Index: 131

Text #3

Max Range: 2.0127. Min Range: -2.0127

Max Act: 1.8526. Min Act: -0.0000

Data Index: 996507 (C4 (Web Text))

Max Activating Token Index: 746

Text #4

Max Range: 2.0127. Min Range: -2.0127

Max Act: 1.7083. Min Act: -0.0000

Data Index: 952969 (C4 (Web Text))

Max Activating Token Index: 4

Text #5

Max Range: 2.0127. Min Range: -2.0127

Max Act: 1.7461. Min Act: 0.0000

Data Index: 803865 (C4 (Web Text))

Max Activating Token Index: 311

Text #6

Max Range: 2.0127. Min Range: -2.0127

Max Act: 1.6416. Min Act: -0.0000

Data Index: 388314 (C4 (Web Text))

Max Activating Token Index: 47

Text #7

Max Range: 2.0127. Min Range: -2.0127

Max Act: 1.5341. Min Act: -0.0000

Data Index: 1245059 (C4 (Web Text))

Max Activating Token Index: 681

Text #8

Max Range: 2.0127. Min Range: -2.0127

Max Act: 1.6032. Min Act: -0.0000

Data Index: 1088306 (C4 (Web Text))

Max Activating Token Index: 454

Text #9

Max Range: 2.0127. Min Range: -2.0127

Max Act: 1.5770. Min Act: -0.0000

Data Index: 488013 (C4 (Web Text))

Max Activating Token Index: 389

Text #10

Max Range: 2.0127. Min Range: -2.0127

Max Act: 1.5541. Min Act: 0.0000

Data Index: 326326 (C4 (Web Text))

Max Activating Token Index: 514

Text #11

Max Range: 2.0127. Min Range: -2.0127

Max Act: 1.4679. Min Act: -0.0000

Data Index: 1351067 (C4 (Web Text))

Max Activating Token Index: 701

Text #12

Max Range: 2.0127. Min Range: -2.0127

Max Act: 1.4333. Min Act: -0.0000

Data Index: 910407 (C4 (Web Text))

Max Activating Token Index: 177

Text #13

Max Range: 2.0127. Min Range: -2.0127

Max Act: 1.5236. Min Act: -0.0000

Data Index: 1063414 (C4 (Web Text))

Max Activating Token Index: 657

Text #14

Max Range: 2.0127. Min Range: -2.0127

Max Act: 1.4365. Min Act: -0.0000

Data Index: 306653 (C4 (Web Text))

Max Activating Token Index: 48

Text #15

Max Range: 2.0127. Min Range: -2.0127

Max Act: 1.4584. Min Act: -0.0000

Data Index: 112678 (C4 (Web Text))

Max Activating Token Index: 630

Text #16

Max Range: 2.0127. Min Range: -2.0127

Max Act: 1.3536. Min Act: -0.0000

Data Index: 633825 (C4 (Web Text))

Max Activating Token Index: 168

Text #17

Max Range: 2.0127. Min Range: -2.0127

Max Act: 1.4282. Min Act: -0.0000

Data Index: 333977 (C4 (Web Text))

Max Activating Token Index: 72

Text #18

Max Range: 2.0127. Min Range: -2.0127

Max Act: 1.4088. Min Act: -0.0000

Data Index: 30515 (C4 (Web Text))

Max Activating Token Index: 26

Text #19

Max Range: 2.0127. Min Range: -2.0127

Max Act: 1.4950. Min Act: -0.0000

Data Index: 448023 (C4 (Web Text))

Max Activating Token Index: 960