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

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

Neuron 1935 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: 0.8031. Min Range: -0.8031

Max Act: 0.8031. Min Act: -0.0000

Data Index: 919378 (C4 (Web Text))

Max Activating Token Index: 110

Text #1

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.7017. Min Act: -0.0001

Data Index: 568772 (C4 (Web Text))

Max Activating Token Index: 706

Text #2

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.7219. Min Act: -0.0001

Data Index: 589084 (C4 (Web Text))

Max Activating Token Index: 647

Text #3

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.7365. Min Act: -0.0001

Data Index: 1258193 (C4 (Web Text))

Max Activating Token Index: 669

Text #4

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.7538. Min Act: -0.0001

Data Index: 957145 (C4 (Web Text))

Max Activating Token Index: 541

Text #5

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.7252. Min Act: -0.0001

Data Index: 794053 (C4 (Web Text))

Max Activating Token Index: 815

Text #6

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.6939. Min Act: -0.0001

Data Index: 782442 (C4 (Web Text))

Max Activating Token Index: 567

Text #7

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.6669. Min Act: -0.0001

Data Index: 928523 (C4 (Web Text))

Max Activating Token Index: 781

Text #8

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.6823. Min Act: -0.0001

Data Index: 554107 (C4 (Web Text))

Max Activating Token Index: 921

Text #9

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.6988. Min Act: -0.0001

Data Index: 898237 (C4 (Web Text))

Max Activating Token Index: 942

Text #10

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.7197. Min Act: -0.0001

Data Index: 339706 (C4 (Web Text))

Max Activating Token Index: 678

Text #11

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.6371. Min Act: -0.0001

Data Index: 947749 (C4 (Web Text))

Max Activating Token Index: 153

Text #12

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.6288. Min Act: -0.0001

Data Index: 536850 (C4 (Web Text))

Max Activating Token Index: 345

Text #13

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.6191. Min Act: -0.0001

Data Index: 872249 (C4 (Web Text))

Max Activating Token Index: 58

Text #14

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.6412. Min Act: -0.0001

Data Index: 1318360 (C4 (Web Text))

Max Activating Token Index: 886

Text #15

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.5976. Min Act: -0.0001

Data Index: 1120465 (C4 (Web Text))

Max Activating Token Index: 960

Text #16

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.6451. Min Act: -0.0001

Data Index: 78173 (C4 (Web Text))

Max Activating Token Index: 247

Text #17

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.6401. Min Act: -0.0001

Data Index: 1299918 (C4 (Web Text))

Max Activating Token Index: 936

Text #18

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.6112. Min Act: -0.0001

Data Index: 1171008 (C4 (Web Text))

Max Activating Token Index: 817

Text #19

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.5903. Min Act: -0.0001

Data Index: 84356 (C4 (Web Text))

Max Activating Token Index: 598