Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1674 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 2.2383. Min Range: -2.2383

Max Act: 2.2383. Min Act: -0.0000

Data Index: 231020 (C4 (Web Text))

Max Activating Token Index: 896

Text #1

Max Range: 2.2383. Min Range: -2.2383

Max Act: 1.9359. Min Act: -0.0001

Data Index: 718013 (C4 (Web Text))

Max Activating Token Index: 847

Text #2

Max Range: 2.2383. Min Range: -2.2383

Max Act: 1.7875. Min Act: -0.0000

Data Index: 442186 (C4 (Web Text))

Max Activating Token Index: 784

Text #3

Max Range: 2.2383. Min Range: -2.2383

Max Act: 1.7916. Min Act: -0.0000

Data Index: 59964 (C4 (Web Text))

Max Activating Token Index: 673

Text #4

Max Range: 2.2383. Min Range: -2.2383

Max Act: 1.8463. Min Act: -0.0000

Data Index: 517963 (C4 (Web Text))

Max Activating Token Index: 467

Text #5

Max Range: 2.2383. Min Range: -2.2383

Max Act: 1.6728. Min Act: -0.0001

Data Index: 283983 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 2.2383. Min Range: -2.2383

Max Act: 1.7388. Min Act: -0.0000

Data Index: 966617 (C4 (Web Text))

Max Activating Token Index: 602

Text #7

Max Range: 2.2383. Min Range: -2.2383

Max Act: 1.5880. Min Act: -0.0001

Data Index: 1084261 (C4 (Web Text))

Max Activating Token Index: 551

Text #8

Max Range: 2.2383. Min Range: -2.2383

Max Act: 1.5693. Min Act: -0.0001

Data Index: 1324156 (C4 (Web Text))

Max Activating Token Index: 55

Text #9

Max Range: 2.2383. Min Range: -2.2383

Max Act: 1.5836. Min Act: -0.0000

Data Index: 1213412 (C4 (Web Text))

Max Activating Token Index: 883

Text #10

Max Range: 2.2383. Min Range: -2.2383

Max Act: 1.5102. Min Act: -0.0000

Data Index: 1293089 (C4 (Web Text))

Max Activating Token Index: 541

Text #11

Max Range: 2.2383. Min Range: -2.2383

Max Act: 1.4505. Min Act: -0.0000

Data Index: 451300 (C4 (Web Text))

Max Activating Token Index: 150

Text #12

Max Range: 2.2383. Min Range: -2.2383

Max Act: 1.4448. Min Act: -0.0001

Data Index: 1231211 (C4 (Web Text))

Max Activating Token Index: 185

Text #13

Max Range: 2.2383. Min Range: -2.2383

Max Act: 1.5214. Min Act: -0.0001

Data Index: 302843 (C4 (Web Text))

Max Activating Token Index: 120

Text #14

Max Range: 2.2383. Min Range: -2.2383

Max Act: 1.4958. Min Act: -0.0000

Data Index: 999073 (C4 (Web Text))

Max Activating Token Index: 575

Text #15

Max Range: 2.2383. Min Range: -2.2383

Max Act: 1.4974. Min Act: -0.0000

Data Index: 114059 (C4 (Web Text))

Max Activating Token Index: 810

Text #16

Max Range: 2.2383. Min Range: -2.2383

Max Act: 1.4641. Min Act: -0.0001

Data Index: 741018 (C4 (Web Text))

Max Activating Token Index: 302

Text #17

Max Range: 2.2383. Min Range: -2.2383

Max Act: 1.4120. Min Act: -0.0001

Data Index: 267794 (C4 (Web Text))

Max Activating Token Index: 53

Text #18

Max Range: 2.2383. Min Range: -2.2383

Max Act: 1.3982. Min Act: -0.0001

Data Index: 373291 (C4 (Web Text))

Max Activating Token Index: 812

Text #19

Max Range: 2.2383. Min Range: -2.2383

Max Act: 1.3112. Min Act: -0.0001

Data Index: 654251 (C4 (Web Text))

Max Activating Token Index: 713