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

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

Neuron 980 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6541. Min Range: -1.6541

Max Act: 1.6541. Min Act: -0.0001

Data Index: 235970 (C4 (Web Text))

Max Activating Token Index: 345

Text #1

Max Range: 1.6541. Min Range: -1.6541

Max Act: 0.9543. Min Act: -0.0001

Data Index: 1190535 (C4 (Web Text))

Max Activating Token Index: 826

Text #2

Max Range: 1.6541. Min Range: -1.6541

Max Act: 1.0050. Min Act: -0.0001

Data Index: 185049 (C4 (Web Text))

Max Activating Token Index: 146

Text #3

Max Range: 1.6541. Min Range: -1.6541

Max Act: 1.0015. Min Act: -0.0001

Data Index: 328185 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 1.6541. Min Range: -1.6541

Max Act: 0.9845. Min Act: -0.0001

Data Index: 1309354 (C4 (Web Text))

Max Activating Token Index: 530

Text #5

Max Range: 1.6541. Min Range: -1.6541

Max Act: 0.9748. Min Act: -0.0001

Data Index: 1251420 (C4 (Web Text))

Max Activating Token Index: 508

Text #6

Max Range: 1.6541. Min Range: -1.6541

Max Act: 0.9448. Min Act: -0.0001

Data Index: 305178 (C4 (Web Text))

Max Activating Token Index: 711

Text #7

Max Range: 1.6541. Min Range: -1.6541

Max Act: 0.9463. Min Act: -0.0001

Data Index: 1219094 (C4 (Web Text))

Max Activating Token Index: 128

Text #8

Max Range: 1.6541. Min Range: -1.6541

Max Act: 0.9510. Min Act: -0.0001

Data Index: 229656 (C4 (Web Text))

Max Activating Token Index: 462

Text #9

Max Range: 1.6541. Min Range: -1.6541

Max Act: 0.9400. Min Act: -0.0001

Data Index: 880725 (C4 (Web Text))

Max Activating Token Index: 675

Text #10

Max Range: 1.6541. Min Range: -1.6541

Max Act: 0.9403. Min Act: -0.0001

Data Index: 635906 (C4 (Web Text))

Max Activating Token Index: 149

Text #11

Max Range: 1.6541. Min Range: -1.6541

Max Act: 0.8975. Min Act: -0.0001

Data Index: 660440 (C4 (Web Text))

Max Activating Token Index: 750

Text #12

Max Range: 1.6541. Min Range: -1.6541

Max Act: 0.8946. Min Act: -0.0001

Data Index: 187025 (C4 (Web Text))

Max Activating Token Index: 800

Text #13

Max Range: 1.6541. Min Range: -1.6541

Max Act: 0.9385. Min Act: -0.0001

Data Index: 1106908 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 1.6541. Min Range: -1.6541

Max Act: 0.9156. Min Act: -0.0001

Data Index: 1195616 (C4 (Web Text))

Max Activating Token Index: 40

Text #15

Max Range: 1.6541. Min Range: -1.6541

Max Act: 0.9104. Min Act: -0.0001

Data Index: 1297548 (C4 (Web Text))

Max Activating Token Index: 38

Text #16

Max Range: 1.6541. Min Range: -1.6541

Max Act: 0.9029. Min Act: -0.0001

Data Index: 520601 (C4 (Web Text))

Max Activating Token Index: 96

Text #17

Max Range: 1.6541. Min Range: -1.6541

Max Act: 0.8926. Min Act: -0.0001

Data Index: 261585 (C4 (Web Text))

Max Activating Token Index: 394

Text #18

Max Range: 1.6541. Min Range: -1.6541

Max Act: 0.8902. Min Act: -0.0001

Data Index: 992994 (C4 (Web Text))

Max Activating Token Index: 171

Text #19

Max Range: 1.6541. Min Range: -1.6541

Max Act: 0.8375. Min Act: -0.0001

Data Index: 271025 (C4 (Web Text))

Max Activating Token Index: 851