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

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

Neuron 2888 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4032. Min Range: -0.4032

Max Act: 0.3941. Min Act: -0.0001

Data Index: 1332143 (C4 (Web Text))

Max Activating Token Index: 793

Text #1

Max Range: 0.4032. Min Range: -0.4032

Max Act: 0.4032. Min Act: -0.0001

Data Index: 1273075 (C4 (Web Text))

Max Activating Token Index: 992

Text #2

Max Range: 0.4032. Min Range: -0.4032

Max Act: 0.3635. Min Act: -0.0001

Data Index: 474111 (C4 (Web Text))

Max Activating Token Index: 675

Text #3

Max Range: 0.4032. Min Range: -0.4032

Max Act: 0.3500. Min Act: -0.0001

Data Index: 984861 (C4 (Web Text))

Max Activating Token Index: 220

Text #4

Max Range: 0.4032. Min Range: -0.4032

Max Act: 0.3373. Min Act: -0.0001

Data Index: 211925 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 0.4032. Min Range: -0.4032

Max Act: 0.3136. Min Act: -0.0001

Data Index: 276664 (C4 (Web Text))

Max Activating Token Index: 700

Text #6

Max Range: 0.4032. Min Range: -0.4032

Max Act: 0.3432. Min Act: -0.0001

Data Index: 323995 (C4 (Web Text))

Max Activating Token Index: 864

Text #7

Max Range: 0.4032. Min Range: -0.4032

Max Act: 0.3060. Min Act: -0.0001

Data Index: 753682 (C4 (Web Text))

Max Activating Token Index: 506

Text #8

Max Range: 0.4032. Min Range: -0.4032

Max Act: 0.3275. Min Act: -0.0001

Data Index: 763810 (C4 (Web Text))

Max Activating Token Index: 839

Text #9

Max Range: 0.4032. Min Range: -0.4032

Max Act: 0.3364. Min Act: -0.0001

Data Index: 95492 (C4 (Web Text))

Max Activating Token Index: 45

Text #10

Max Range: 0.4032. Min Range: -0.4032

Max Act: 0.3363. Min Act: -0.0001

Data Index: 946714 (C4 (Web Text))

Max Activating Token Index: 24

Text #11

Max Range: 0.4032. Min Range: -0.4032

Max Act: 0.2900. Min Act: -0.0001

Data Index: 498108 (C4 (Web Text))

Max Activating Token Index: 539

Text #12

Max Range: 0.4032. Min Range: -0.4032

Max Act: 0.3103. Min Act: -0.0001

Data Index: 122245 (C4 (Web Text))

Max Activating Token Index: 696

Text #13

Max Range: 0.4032. Min Range: -0.4032

Max Act: 0.3104. Min Act: -0.0001

Data Index: 518787 (C4 (Web Text))

Max Activating Token Index: 439

Text #14

Max Range: 0.4032. Min Range: -0.4032

Max Act: 0.3051. Min Act: -0.0001

Data Index: 1178236 (C4 (Web Text))

Max Activating Token Index: 555

Text #15

Max Range: 0.4032. Min Range: -0.4032

Max Act: 0.3047. Min Act: -0.0001

Data Index: 991096 (C4 (Web Text))

Max Activating Token Index: 502

Text #16

Max Range: 0.4032. Min Range: -0.4032

Max Act: 0.2895. Min Act: -0.0001

Data Index: 635218 (C4 (Web Text))

Max Activating Token Index: 839

Text #17

Max Range: 0.4032. Min Range: -0.4032

Max Act: 0.3340. Min Act: -0.0001

Data Index: 431236 (C4 (Web Text))

Max Activating Token Index: 668

Text #18

Max Range: 0.4032. Min Range: -0.4032

Max Act: 0.3114. Min Act: -0.0001

Data Index: 1195239 (C4 (Web Text))

Max Activating Token Index: 829

Text #19

Max Range: 0.4032. Min Range: -0.4032

Max Act: 0.2974. Min Act: -0.0001

Data Index: 1157107 (C4 (Web Text))

Max Activating Token Index: 703