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

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

Neuron 2913 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.4788. Min Act: -0.0000

Data Index: 48634 (C4 (Web Text))

Max Activating Token Index: 768

Text #1

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.4301. Min Act: -0.0001

Data Index: 947190 (C4 (Web Text))

Max Activating Token Index: 1001

Text #2

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.3970. Min Act: -0.0001

Data Index: 1034575 (C4 (Web Text))

Max Activating Token Index: 689

Text #3

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.3654. Min Act: -0.0000

Data Index: 1059726 (C4 (Web Text))

Max Activating Token Index: 169

Text #4

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.3433. Min Act: -0.0001

Data Index: 779239 (C4 (Web Text))

Max Activating Token Index: 549

Text #5

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.3296. Min Act: -0.0000

Data Index: 1105800 (C4 (Web Text))

Max Activating Token Index: 139

Text #6

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.3107. Min Act: -0.0000

Data Index: 1021572 (C4 (Web Text))

Max Activating Token Index: 618

Text #7

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.3118. Min Act: -0.0000

Data Index: 535360 (C4 (Web Text))

Max Activating Token Index: 333

Text #8

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.3134. Min Act: -0.0000

Data Index: 492725 (C4 (Web Text))

Max Activating Token Index: 835

Text #9

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.3114. Min Act: -0.0000

Data Index: 256164 (C4 (Web Text))

Max Activating Token Index: 589

Text #10

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.3203. Min Act: -0.0000

Data Index: 42871 (C4 (Web Text))

Max Activating Token Index: 752

Text #11

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.3052. Min Act: -0.0000

Data Index: 814928 (C4 (Web Text))

Max Activating Token Index: 30

Text #12

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.3159. Min Act: -0.0000

Data Index: 909982 (C4 (Web Text))

Max Activating Token Index: 288

Text #13

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.2920. Min Act: -0.0000

Data Index: 631772 (C4 (Web Text))

Max Activating Token Index: 1020

Text #14

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.3022. Min Act: -0.0001

Data Index: 1234405 (C4 (Web Text))

Max Activating Token Index: 848

Text #15

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.2992. Min Act: -0.0000

Data Index: 259571 (C4 (Web Text))

Max Activating Token Index: 592

Text #16

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.2871. Min Act: -0.0001

Data Index: 199213 (C4 (Web Text))

Max Activating Token Index: 209

Text #17

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.3065. Min Act: -0.0000

Data Index: 188224 (C4 (Web Text))

Max Activating Token Index: 235

Text #18

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.2968. Min Act: -0.0000

Data Index: 780416 (C4 (Web Text))

Max Activating Token Index: 520

Text #19

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.2948. Min Act: -0.0000

Data Index: 278281 (C4 (Web Text))

Max Activating Token Index: 735