Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5345 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.4990. Min Range: -0.4990

Max Act: 0.4962. Min Act: -0.0001

Data Index: 797329 (C4 (Web Text))

Max Activating Token Index: 338

Text #1

Max Range: 0.4990. Min Range: -0.4990

Max Act: 0.4982. Min Act: -0.0001

Data Index: 1005227 (C4 (Web Text))

Max Activating Token Index: 593

Text #2

Max Range: 0.4990. Min Range: -0.4990

Max Act: 0.4990. Min Act: -0.0001

Data Index: 884864 (C4 (Web Text))

Max Activating Token Index: 567

Text #3

Max Range: 0.4990. Min Range: -0.4990

Max Act: 0.4817. Min Act: -0.0001

Data Index: 122985 (C4 (Web Text))

Max Activating Token Index: 375

Text #4

Max Range: 0.4990. Min Range: -0.4990

Max Act: 0.4857. Min Act: -0.0001

Data Index: 860069 (C4 (Web Text))

Max Activating Token Index: 730

Text #5

Max Range: 0.4990. Min Range: -0.4990

Max Act: 0.4867. Min Act: -0.0001

Data Index: 783930 (C4 (Web Text))

Max Activating Token Index: 899

Text #6

Max Range: 0.4990. Min Range: -0.4990

Max Act: 0.4628. Min Act: -0.0001

Data Index: 262538 (C4 (Web Text))

Max Activating Token Index: 74

Text #7

Max Range: 0.4990. Min Range: -0.4990

Max Act: 0.4508. Min Act: -0.0001

Data Index: 163929 (C4 (Web Text))

Max Activating Token Index: 789

Text #8

Max Range: 0.4990. Min Range: -0.4990

Max Act: 0.4582. Min Act: -0.0002

Data Index: 1097004 (C4 (Web Text))

Max Activating Token Index: 499

Text #9

Max Range: 0.4990. Min Range: -0.4990

Max Act: 0.4427. Min Act: -0.0001

Data Index: 437070 (C4 (Web Text))

Max Activating Token Index: 8

Text #10

Max Range: 0.4990. Min Range: -0.4990

Max Act: 0.4445. Min Act: -0.0001

Data Index: 844591 (C4 (Web Text))

Max Activating Token Index: 427

Text #11

Max Range: 0.4990. Min Range: -0.4990

Max Act: 0.4272. Min Act: -0.0001

Data Index: 918681 (C4 (Web Text))

Max Activating Token Index: 1001

Text #12

Max Range: 0.4990. Min Range: -0.4990

Max Act: 0.4197. Min Act: -0.0001

Data Index: 876877 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.4990. Min Range: -0.4990

Max Act: 0.4233. Min Act: -0.0002

Data Index: 795947 (C4 (Web Text))

Max Activating Token Index: 232

Text #14

Max Range: 0.4990. Min Range: -0.4990

Max Act: 0.4211. Min Act: -0.0001

Data Index: 135364 (C4 (Web Text))

Max Activating Token Index: 208

Text #15

Max Range: 0.4990. Min Range: -0.4990

Max Act: 0.4140. Min Act: -0.0001

Data Index: 115865 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.4990. Min Range: -0.4990

Max Act: 0.4161. Min Act: -0.0001

Data Index: 980758 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.4990. Min Range: -0.4990

Max Act: 0.4094. Min Act: -0.0001

Data Index: 422753 (C4 (Web Text))

Max Activating Token Index: 881

Text #18

Max Range: 0.4990. Min Range: -0.4990

Max Act: 0.4127. Min Act: -0.0001

Data Index: 101097 (C4 (Web Text))

Max Activating Token Index: 173

Text #19

Max Range: 0.4990. Min Range: -0.4990

Max Act: 0.4151. Min Act: -0.0001

Data Index: 328416 (C4 (Web Text))

Max Activating Token Index: 672