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

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

Neuron 5026 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: 3.7146. Min Range: -3.7146

Max Act: 3.7146. Min Act: -0.0000

Data Index: 918168 (C4 (Web Text))

Max Activating Token Index: 238

Text #1

Max Range: 3.7146. Min Range: -3.7146

Max Act: 3.3363. Min Act: -0.0000

Data Index: 74330 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 3.7146. Min Range: -3.7146

Max Act: 3.1714. Min Act: -0.0000

Data Index: 496520 (C4 (Web Text))

Max Activating Token Index: 791

Text #3

Max Range: 3.7146. Min Range: -3.7146

Max Act: 3.5825. Min Act: -0.0000

Data Index: 1227526 (C4 (Web Text))

Max Activating Token Index: 320

Text #4

Max Range: 3.7146. Min Range: -3.7146

Max Act: 3.3250. Min Act: -0.0000

Data Index: 1173306 (C4 (Web Text))

Max Activating Token Index: 830

Text #5

Max Range: 3.7146. Min Range: -3.7146

Max Act: 3.4062. Min Act: -0.0000

Data Index: 838046 (C4 (Web Text))

Max Activating Token Index: 944

Text #6

Max Range: 3.7146. Min Range: -3.7146

Max Act: 3.5754. Min Act: -0.0000

Data Index: 409446 (C4 (Web Text))

Max Activating Token Index: 732

Text #7

Max Range: 3.7146. Min Range: -3.7146

Max Act: 3.3465. Min Act: -0.0000

Data Index: 501658 (C4 (Web Text))

Max Activating Token Index: 125

Text #8

Max Range: 3.7146. Min Range: -3.7146

Max Act: 3.0631. Min Act: -0.0000

Data Index: 1132085 (C4 (Web Text))

Max Activating Token Index: 794

Text #9

Max Range: 3.7146. Min Range: -3.7146

Max Act: 2.8918. Min Act: -0.0000

Data Index: 1358892 (C4 (Web Text))

Max Activating Token Index: 172

Text #10

Max Range: 3.7146. Min Range: -3.7146

Max Act: 3.1979. Min Act: -0.0000

Data Index: 188385 (C4 (Web Text))

Max Activating Token Index: 132

Text #11

Max Range: 3.7146. Min Range: -3.7146

Max Act: 3.1927. Min Act: -0.0000

Data Index: 645730 (C4 (Web Text))

Max Activating Token Index: 748

Text #12

Max Range: 3.7146. Min Range: -3.7146

Max Act: 3.0350. Min Act: -0.0000

Data Index: 954597 (C4 (Web Text))

Max Activating Token Index: 166

Text #13

Max Range: 3.7146. Min Range: -3.7146

Max Act: 2.7139. Min Act: -0.0000

Data Index: 1324731 (C4 (Web Text))

Max Activating Token Index: 643

Text #14

Max Range: 3.7146. Min Range: -3.7146

Max Act: 2.7994. Min Act: -0.0000

Data Index: 1230121 (C4 (Web Text))

Max Activating Token Index: 301

Text #15

Max Range: 3.7146. Min Range: -3.7146

Max Act: 2.9195. Min Act: -0.0000

Data Index: 678068 (C4 (Web Text))

Max Activating Token Index: 340

Text #16

Max Range: 3.7146. Min Range: -3.7146

Max Act: 2.9358. Min Act: -0.0000

Data Index: 277632 (C4 (Web Text))

Max Activating Token Index: 13

Text #17

Max Range: 3.7146. Min Range: -3.7146

Max Act: 2.6442. Min Act: -0.0000

Data Index: 692298 (C4 (Web Text))

Max Activating Token Index: 178

Text #18

Max Range: 3.7146. Min Range: -3.7146

Max Act: 2.9002. Min Act: -0.0000

Data Index: 1319337 (C4 (Web Text))

Max Activating Token Index: 916

Text #19

Max Range: 3.7146. Min Range: -3.7146

Max Act: 2.8868. Min Act: -0.0000

Data Index: 626310 (C4 (Web Text))

Max Activating Token Index: 546