Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 193 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.9993. Min Act: -0.0001

Data Index: 676758 (C4 (Web Text))

Max Activating Token Index: 93

Text #1

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.8407. Min Act: -0.0001

Data Index: 1350438 (C4 (Web Text))

Max Activating Token Index: 268

Text #2

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.7897. Min Act: -0.0001

Data Index: 238201 (C4 (Web Text))

Max Activating Token Index: 187

Text #3

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.7968. Min Act: -0.0001

Data Index: 680386 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.8124. Min Act: -0.0001

Data Index: 659258 (C4 (Web Text))

Max Activating Token Index: 854

Text #5

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.7953. Min Act: -0.0001

Data Index: 690725 (C4 (Web Text))

Max Activating Token Index: 377

Text #6

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.7822. Min Act: -0.0001

Data Index: 241545 (C4 (Web Text))

Max Activating Token Index: 410

Text #7

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.7502. Min Act: -0.0001

Data Index: 862312 (C4 (Web Text))

Max Activating Token Index: 402

Text #8

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.6962. Min Act: -0.0001

Data Index: 745619 (C4 (Web Text))

Max Activating Token Index: 414

Text #9

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.6881. Min Act: -0.0001

Data Index: 96907 (C4 (Web Text))

Max Activating Token Index: 2

Text #10

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.7237. Min Act: -0.0001

Data Index: 1207629 (C4 (Web Text))

Max Activating Token Index: 911

Text #11

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.6955. Min Act: -0.0001

Data Index: 1342535 (C4 (Web Text))

Max Activating Token Index: 718

Text #12

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.6751. Min Act: -0.0001

Data Index: 19381 (C4 (Web Text))

Max Activating Token Index: 222

Text #13

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.7373. Min Act: -0.0001

Data Index: 921280 (C4 (Web Text))

Max Activating Token Index: 128

Text #14

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.6938. Min Act: -0.0001

Data Index: 493228 (C4 (Web Text))

Max Activating Token Index: 11

Text #15

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.7171. Min Act: -0.0001

Data Index: 1293277 (C4 (Web Text))

Max Activating Token Index: 809

Text #16

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.6719. Min Act: -0.0001

Data Index: 881452 (C4 (Web Text))

Max Activating Token Index: 709

Text #17

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.7423. Min Act: -0.0001

Data Index: 527085 (C4 (Web Text))

Max Activating Token Index: 661

Text #18

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.7366. Min Act: -0.0001

Data Index: 146478 (C4 (Web Text))

Max Activating Token Index: 936

Text #19

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.6315. Min Act: -0.0001

Data Index: 1074512 (C4 (Web Text))

Max Activating Token Index: 880