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

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

Neuron 3207 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: 0.2484. Min Range: -0.2484

Max Act: 0.2462. Min Act: -0.0001

Data Index: 535696 (C4 (Web Text))

Max Activating Token Index: 549

Text #1

Max Range: 0.2484. Min Range: -0.2484

Max Act: 0.2320. Min Act: -0.0001

Data Index: 25756 (C4 (Web Text))

Max Activating Token Index: 688

Text #2

Max Range: 0.2484. Min Range: -0.2484

Max Act: 0.2484. Min Act: -0.0000

Data Index: 897869 (C4 (Web Text))

Max Activating Token Index: 1020

Text #3

Max Range: 0.2484. Min Range: -0.2484

Max Act: 0.2464. Min Act: -0.0000

Data Index: 776211 (C4 (Web Text))

Max Activating Token Index: 743

Text #4

Max Range: 0.2484. Min Range: -0.2484

Max Act: 0.2449. Min Act: -0.0000

Data Index: 842108 (C4 (Web Text))

Max Activating Token Index: 895

Text #5

Max Range: 0.2484. Min Range: -0.2484

Max Act: 0.2310. Min Act: -0.0000

Data Index: 134848 (C4 (Web Text))

Max Activating Token Index: 1004

Text #6

Max Range: 0.2484. Min Range: -0.2484

Max Act: 0.2384. Min Act: -0.0000

Data Index: 85999 (C4 (Web Text))

Max Activating Token Index: 638

Text #7

Max Range: 0.2484. Min Range: -0.2484

Max Act: 0.2215. Min Act: -0.0000

Data Index: 1180800 (C4 (Web Text))

Max Activating Token Index: 756

Text #8

Max Range: 0.2484. Min Range: -0.2484

Max Act: 0.2169. Min Act: -0.0000

Data Index: 321158 (C4 (Web Text))

Max Activating Token Index: 454

Text #9

Max Range: 0.2484. Min Range: -0.2484

Max Act: 0.2259. Min Act: -0.0000

Data Index: 552471 (C4 (Web Text))

Max Activating Token Index: 127

Text #10

Max Range: 0.2484. Min Range: -0.2484

Max Act: 0.2128. Min Act: -0.0000

Data Index: 457082 (C4 (Web Text))

Max Activating Token Index: 511

Text #11

Max Range: 0.2484. Min Range: -0.2484

Max Act: 0.2292. Min Act: -0.0000

Data Index: 672700 (C4 (Web Text))

Max Activating Token Index: 356

Text #12

Max Range: 0.2484. Min Range: -0.2484

Max Act: 0.2046. Min Act: -0.0000

Data Index: 377230 (C4 (Web Text))

Max Activating Token Index: 465

Text #13

Max Range: 0.2484. Min Range: -0.2484

Max Act: 0.2039. Min Act: -0.0000

Data Index: 1173914 (C4 (Web Text))

Max Activating Token Index: 533

Text #14

Max Range: 0.2484. Min Range: -0.2484

Max Act: 0.1950. Min Act: -0.0000

Data Index: 16941 (C4 (Web Text))

Max Activating Token Index: 551

Text #15

Max Range: 0.2484. Min Range: -0.2484

Max Act: 0.2050. Min Act: -0.0000

Data Index: 980775 (C4 (Web Text))

Max Activating Token Index: 719

Text #16

Max Range: 0.2484. Min Range: -0.2484

Max Act: 0.2045. Min Act: -0.0000

Data Index: 407184 (C4 (Web Text))

Max Activating Token Index: 979

Text #17

Max Range: 0.2484. Min Range: -0.2484

Max Act: 0.2001. Min Act: -0.0000

Data Index: 936609 (C4 (Web Text))

Max Activating Token Index: 829

Text #18

Max Range: 0.2484. Min Range: -0.2484

Max Act: 0.2052. Min Act: -0.0000

Data Index: 143964 (C4 (Web Text))

Max Activating Token Index: 330

Text #19

Max Range: 0.2484. Min Range: -0.2484

Max Act: 0.2044. Min Act: -0.0000

Data Index: 10455 (C4 (Web Text))

Max Activating Token Index: 961