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

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

Neuron 3256 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: 0.3163. Min Range: -0.3163

Max Act: 0.3163. Min Act: -0.0001

Data Index: 1014964 (C4 (Web Text))

Max Activating Token Index: 694

Text #1

Max Range: 0.3163. Min Range: -0.3163

Max Act: 0.2814. Min Act: -0.0001

Data Index: 723526 (C4 (Web Text))

Max Activating Token Index: 913

Text #2

Max Range: 0.3163. Min Range: -0.3163

Max Act: 0.2772. Min Act: -0.0001

Data Index: 1248840 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 0.3163. Min Range: -0.3163

Max Act: 0.2713. Min Act: -0.0001

Data Index: 1320563 (C4 (Web Text))

Max Activating Token Index: 938

Text #4

Max Range: 0.3163. Min Range: -0.3163

Max Act: 0.2517. Min Act: -0.0001

Data Index: 236017 (C4 (Web Text))

Max Activating Token Index: 689

Text #5

Max Range: 0.3163. Min Range: -0.3163

Max Act: 0.2604. Min Act: -0.0001

Data Index: 1336845 (C4 (Web Text))

Max Activating Token Index: 912

Text #6

Max Range: 0.3163. Min Range: -0.3163

Max Act: 0.2371. Min Act: -0.0001

Data Index: 150453 (C4 (Web Text))

Max Activating Token Index: 372

Text #7

Max Range: 0.3163. Min Range: -0.3163

Max Act: 0.2450. Min Act: -0.0001

Data Index: 693791 (C4 (Web Text))

Max Activating Token Index: 124

Text #8

Max Range: 0.3163. Min Range: -0.3163

Max Act: 0.2304. Min Act: -0.0001

Data Index: 1207602 (C4 (Web Text))

Max Activating Token Index: 44

Text #9

Max Range: 0.3163. Min Range: -0.3163

Max Act: 0.2055. Min Act: -0.0001

Data Index: 157585 (C4 (Web Text))

Max Activating Token Index: 248

Text #10

Max Range: 0.3163. Min Range: -0.3163

Max Act: 0.2371. Min Act: -0.0001

Data Index: 9170 (C4 (Web Text))

Max Activating Token Index: 754

Text #11

Max Range: 0.3163. Min Range: -0.3163

Max Act: 0.2149. Min Act: -0.0001

Data Index: 1147942 (C4 (Web Text))

Max Activating Token Index: 917

Text #12

Max Range: 0.3163. Min Range: -0.3163

Max Act: 0.2147. Min Act: -0.0001

Data Index: 1052277 (C4 (Web Text))

Max Activating Token Index: 996

Text #13

Max Range: 0.3163. Min Range: -0.3163

Max Act: 0.2234. Min Act: -0.0001

Data Index: 188281 (C4 (Web Text))

Max Activating Token Index: 997

Text #14

Max Range: 0.3163. Min Range: -0.3163

Max Act: 0.2115. Min Act: -0.0001

Data Index: 1153590 (C4 (Web Text))

Max Activating Token Index: 744

Text #15

Max Range: 0.3163. Min Range: -0.3163

Max Act: 0.2044. Min Act: -0.0001

Data Index: 572586 (C4 (Web Text))

Max Activating Token Index: 265

Text #16

Max Range: 0.3163. Min Range: -0.3163

Max Act: 0.1962. Min Act: -0.0001

Data Index: 611504 (C4 (Web Text))

Max Activating Token Index: 488

Text #17

Max Range: 0.3163. Min Range: -0.3163

Max Act: 0.2041. Min Act: -0.0001

Data Index: 1279660 (C4 (Web Text))

Max Activating Token Index: 398

Text #18

Max Range: 0.3163. Min Range: -0.3163

Max Act: 0.2028. Min Act: -0.0001

Data Index: 1082648 (C4 (Web Text))

Max Activating Token Index: 917

Text #19

Max Range: 0.3163. Min Range: -0.3163

Max Act: 0.2155. Min Act: -0.0001

Data Index: 933341 (C4 (Web Text))

Max Activating Token Index: 257