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

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

Neuron 2423 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: 1.7594. Min Range: -1.7594

Max Act: 1.6041. Min Act: -0.0001

Data Index: 414651 (C4 (Web Text))

Max Activating Token Index: 577

Text #1

Max Range: 1.7594. Min Range: -1.7594

Max Act: 1.7594. Min Act: -0.0001

Data Index: 948226 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 1.7594. Min Range: -1.7594

Max Act: 1.6847. Min Act: -0.0001

Data Index: 89610 (C4 (Web Text))

Max Activating Token Index: 99

Text #3

Max Range: 1.7594. Min Range: -1.7594

Max Act: 1.5975. Min Act: -0.0001

Data Index: 828201 (C4 (Web Text))

Max Activating Token Index: 173

Text #4

Max Range: 1.7594. Min Range: -1.7594

Max Act: 1.5831. Min Act: -0.0001

Data Index: 461630 (C4 (Web Text))

Max Activating Token Index: 590

Text #5

Max Range: 1.7594. Min Range: -1.7594

Max Act: 1.6287. Min Act: -0.0001

Data Index: 1206342 (C4 (Web Text))

Max Activating Token Index: 169

Text #6

Max Range: 1.7594. Min Range: -1.7594

Max Act: 1.6131. Min Act: -0.0001

Data Index: 882113 (C4 (Web Text))

Max Activating Token Index: 203

Text #7

Max Range: 1.7594. Min Range: -1.7594

Max Act: 1.5125. Min Act: -0.0001

Data Index: 869908 (C4 (Web Text))

Max Activating Token Index: 81

Text #8

Max Range: 1.7594. Min Range: -1.7594

Max Act: 1.5350. Min Act: -0.0001

Data Index: 759174 (C4 (Web Text))

Max Activating Token Index: 378

Text #9

Max Range: 1.7594. Min Range: -1.7594

Max Act: 1.4394. Min Act: -0.0001

Data Index: 211165 (C4 (Web Text))

Max Activating Token Index: 221

Text #10

Max Range: 1.7594. Min Range: -1.7594

Max Act: 1.3937. Min Act: -0.0001

Data Index: 189146 (C4 (Web Text))

Max Activating Token Index: 287

Text #11

Max Range: 1.7594. Min Range: -1.7594

Max Act: 1.5140. Min Act: -0.0001

Data Index: 131588 (C4 (Web Text))

Max Activating Token Index: 489

Text #12

Max Range: 1.7594. Min Range: -1.7594

Max Act: 1.4620. Min Act: -0.0001

Data Index: 261863 (C4 (Web Text))

Max Activating Token Index: 1005

Text #13

Max Range: 1.7594. Min Range: -1.7594

Max Act: 1.4703. Min Act: -0.0001

Data Index: 233971 (C4 (Web Text))

Max Activating Token Index: 624

Text #14

Max Range: 1.7594. Min Range: -1.7594

Max Act: 1.4436. Min Act: -0.0001

Data Index: 648561 (C4 (Web Text))

Max Activating Token Index: 982

Text #15

Max Range: 1.7594. Min Range: -1.7594

Max Act: 1.5324. Min Act: -0.0001

Data Index: 202279 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 1.7594. Min Range: -1.7594

Max Act: 1.5960. Min Act: -0.0001

Data Index: 289375 (C4 (Web Text))

Max Activating Token Index: 915

Text #17

Max Range: 1.7594. Min Range: -1.7594

Max Act: 1.3121. Min Act: -0.0001

Data Index: 758922 (C4 (Web Text))

Max Activating Token Index: 374

Text #18

Max Range: 1.7594. Min Range: -1.7594

Max Act: 1.3721. Min Act: -0.0001

Data Index: 1129317 (C4 (Web Text))

Max Activating Token Index: 997

Text #19

Max Range: 1.7594. Min Range: -1.7594

Max Act: 1.4396. Min Act: -0.0001

Data Index: 492107 (C4 (Web Text))

Max Activating Token Index: 689