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

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

Neuron 2558 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: 0.1336. Min Range: -0.1336

Max Act: 0.1279. Min Act: -0.0001

Data Index: 458217 (C4 (Web Text))

Max Activating Token Index: 705

Text #1

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1336. Min Act: -0.0002

Data Index: 1119752 (C4 (Web Text))

Max Activating Token Index: 785

Text #2

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1233. Min Act: -0.0002

Data Index: 666858 (C4 (Web Text))

Max Activating Token Index: 1003

Text #3

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1182. Min Act: -0.0002

Data Index: 38763 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1171. Min Act: -0.0002

Data Index: 586031 (C4 (Web Text))

Max Activating Token Index: 623

Text #5

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1132. Min Act: -0.0002

Data Index: 1319470 (C4 (Web Text))

Max Activating Token Index: 862

Text #6

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1176. Min Act: -0.0001

Data Index: 468175 (C4 (Web Text))

Max Activating Token Index: 452

Text #7

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1085. Min Act: -0.0001

Data Index: 516655 (C4 (Web Text))

Max Activating Token Index: 989

Text #8

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1158. Min Act: -0.0002

Data Index: 698030 (C4 (Web Text))

Max Activating Token Index: 332

Text #9

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1114. Min Act: -0.0002

Data Index: 799530 (C4 (Web Text))

Max Activating Token Index: 639

Text #10

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1078. Min Act: -0.0001

Data Index: 179323 (C4 (Web Text))

Max Activating Token Index: 867

Text #11

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1050. Min Act: -0.0002

Data Index: 1177776 (C4 (Web Text))

Max Activating Token Index: 300

Text #12

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1043. Min Act: -0.0001

Data Index: 867587 (C4 (Web Text))

Max Activating Token Index: 742

Text #13

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1036. Min Act: -0.0002

Data Index: 1010970 (C4 (Web Text))

Max Activating Token Index: 394

Text #14

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1062. Min Act: -0.0002

Data Index: 754605 (C4 (Web Text))

Max Activating Token Index: 144

Text #15

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1090. Min Act: -0.0002

Data Index: 371808 (C4 (Web Text))

Max Activating Token Index: 854

Text #16

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1009. Min Act: -0.0002

Data Index: 1103754 (C4 (Web Text))

Max Activating Token Index: 982

Text #17

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1049. Min Act: -0.0001

Data Index: 995116 (C4 (Web Text))

Max Activating Token Index: 288

Text #18

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.0950. Min Act: -0.0001

Data Index: 162113 (C4 (Web Text))

Max Activating Token Index: 948

Text #19

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1013. Min Act: -0.0002

Data Index: 969099 (C4 (Web Text))

Max Activating Token Index: 920