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

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

Neuron 2329 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1386. Min Act: -0.0001

Data Index: 760167 (C4 (Web Text))

Max Activating Token Index: 576

Text #1

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1304. Min Act: -0.0001

Data Index: 929260 (C4 (Web Text))

Max Activating Token Index: 591

Text #2

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1265. Min Act: -0.0001

Data Index: 1201648 (C4 (Web Text))

Max Activating Token Index: 846

Text #3

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1192. Min Act: -0.0002

Data Index: 580551 (C4 (Web Text))

Max Activating Token Index: 332

Text #4

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1180. Min Act: -0.0001

Data Index: 1181457 (C4 (Web Text))

Max Activating Token Index: 26

Text #5

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1178. Min Act: -0.0001

Data Index: 706634 (C4 (Web Text))

Max Activating Token Index: 970

Text #6

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1182. Min Act: -0.0001

Data Index: 1050283 (C4 (Web Text))

Max Activating Token Index: 119

Text #7

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1237. Min Act: -0.0001

Data Index: 1144899 (C4 (Web Text))

Max Activating Token Index: 508

Text #8

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1150. Min Act: -0.0002

Data Index: 348021 (C4 (Web Text))

Max Activating Token Index: 912

Text #9

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1016. Min Act: -0.0001

Data Index: 56916 (C4 (Web Text))

Max Activating Token Index: 875

Text #10

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1021. Min Act: -0.0001

Data Index: 1188969 (C4 (Web Text))

Max Activating Token Index: 863

Text #11

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1014. Min Act: -0.0001

Data Index: 837237 (C4 (Web Text))

Max Activating Token Index: 835

Text #12

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.0960. Min Act: -0.0001

Data Index: 495494 (C4 (Web Text))

Max Activating Token Index: 621

Text #13

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1028. Min Act: -0.0002

Data Index: 1220759 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.0987. Min Act: -0.0001

Data Index: 453734 (C4 (Web Text))

Max Activating Token Index: 644

Text #15

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.0949. Min Act: -0.0001

Data Index: 917211 (C4 (Web Text))

Max Activating Token Index: 632

Text #16

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.0979. Min Act: -0.0001

Data Index: 172045 (C4 (Web Text))

Max Activating Token Index: 185

Text #17

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1058. Min Act: -0.0002

Data Index: 442281 (C4 (Web Text))

Max Activating Token Index: 705

Text #18

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.0956. Min Act: -0.0002

Data Index: 1004632 (C4 (Web Text))

Max Activating Token Index: 471

Text #19

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1018. Min Act: -0.0001

Data Index: 1224429 (C4 (Web Text))

Max Activating Token Index: 172