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

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

Neuron 3924 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: 0.1329. Min Range: -0.1329

Max Act: 0.1319. Min Act: -0.0000

Data Index: 1147267 (C4 (Web Text))

Max Activating Token Index: 821

Text #1

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1296. Min Act: -0.0000

Data Index: 317091 (C4 (Web Text))

Max Activating Token Index: 80

Text #2

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1329. Min Act: -0.0001

Data Index: 1084534 (C4 (Web Text))

Max Activating Token Index: 594

Text #3

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1177. Min Act: -0.0001

Data Index: 1199019 (C4 (Web Text))

Max Activating Token Index: 201

Text #4

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1181. Min Act: -0.0000

Data Index: 1262835 (C4 (Web Text))

Max Activating Token Index: 67

Text #5

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1086. Min Act: -0.0000

Data Index: 983337 (C4 (Web Text))

Max Activating Token Index: 569

Text #6

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1136. Min Act: -0.0001

Data Index: 511674 (C4 (Web Text))

Max Activating Token Index: 764

Text #7

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1011. Min Act: -0.0001

Data Index: 1442118 (Python Code)

Max Activating Token Index: 642

Text #8

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1111. Min Act: -0.0001

Data Index: 1610616 (Python Code)

Max Activating Token Index: 588

Text #9

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1020. Min Act: -0.0001

Data Index: 108772 (C4 (Web Text))

Max Activating Token Index: 539

Text #10

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1088. Min Act: -0.0001

Data Index: 1364227 (Python Code)

Max Activating Token Index: 982

Text #11

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1103. Min Act: -0.0001

Data Index: 1572700 (Python Code)

Max Activating Token Index: 380

Text #12

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1093. Min Act: -0.0000

Data Index: 921576 (C4 (Web Text))

Max Activating Token Index: 701

Text #13

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1006. Min Act: -0.0000

Data Index: 887212 (C4 (Web Text))

Max Activating Token Index: 741

Text #14

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1106. Min Act: -0.0001

Data Index: 939849 (C4 (Web Text))

Max Activating Token Index: 210

Text #15

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1071. Min Act: -0.0000

Data Index: 390569 (C4 (Web Text))

Max Activating Token Index: 100

Text #16

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1052. Min Act: -0.0001

Data Index: 1522277 (Python Code)

Max Activating Token Index: 646

Text #17

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.0943. Min Act: -0.0000

Data Index: 177654 (C4 (Web Text))

Max Activating Token Index: 367

Text #18

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1002. Min Act: -0.0001

Data Index: 1064249 (C4 (Web Text))

Max Activating Token Index: 113

Text #19

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1056. Min Act: -0.0000

Data Index: 793807 (C4 (Web Text))

Max Activating Token Index: 122