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

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

Neuron 6023 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.4343. Min Range: -7.4343

Max Act: 7.4343. Min Act: -0.0000

Data Index: 379116 (C4 (Web Text))

Max Activating Token Index: 474

Text #1

Max Range: 7.4343. Min Range: -7.4343

Max Act: 7.2712. Min Act: -0.0000

Data Index: 1099857 (C4 (Web Text))

Max Activating Token Index: 278

Text #2

Max Range: 7.4343. Min Range: -7.4343

Max Act: 7.2710. Min Act: -0.0000

Data Index: 39247 (C4 (Web Text))

Max Activating Token Index: 226

Text #3

Max Range: 7.4343. Min Range: -7.4343

Max Act: 7.2676. Min Act: -0.0000

Data Index: 1210964 (C4 (Web Text))

Max Activating Token Index: 215

Text #4

Max Range: 7.4343. Min Range: -7.4343

Max Act: 7.0161. Min Act: -0.0000

Data Index: 698009 (C4 (Web Text))

Max Activating Token Index: 103

Text #5

Max Range: 7.4343. Min Range: -7.4343

Max Act: 7.1654. Min Act: -0.0000

Data Index: 1309756 (C4 (Web Text))

Max Activating Token Index: 388

Text #6

Max Range: 7.4343. Min Range: -7.4343

Max Act: 7.3201. Min Act: -0.0000

Data Index: 49396 (C4 (Web Text))

Max Activating Token Index: 511

Text #7

Max Range: 7.4343. Min Range: -7.4343

Max Act: 7.0933. Min Act: -0.0000

Data Index: 914837 (C4 (Web Text))

Max Activating Token Index: 453

Text #8

Max Range: 7.4343. Min Range: -7.4343

Max Act: 7.0308. Min Act: -0.0000

Data Index: 1084239 (C4 (Web Text))

Max Activating Token Index: 130

Text #9

Max Range: 7.4343. Min Range: -7.4343

Max Act: 6.9754. Min Act: -0.0000

Data Index: 1138946 (C4 (Web Text))

Max Activating Token Index: 401

Text #10

Max Range: 7.4343. Min Range: -7.4343

Max Act: 6.8801. Min Act: -0.0000

Data Index: 879628 (C4 (Web Text))

Max Activating Token Index: 440

Text #11

Max Range: 7.4343. Min Range: -7.4343

Max Act: 6.7087. Min Act: -0.0000

Data Index: 1308750 (C4 (Web Text))

Max Activating Token Index: 317

Text #12

Max Range: 7.4343. Min Range: -7.4343

Max Act: 7.2578. Min Act: -0.0000

Data Index: 148818 (C4 (Web Text))

Max Activating Token Index: 731

Text #13

Max Range: 7.4343. Min Range: -7.4343

Max Act: 6.6971. Min Act: -0.0000

Data Index: 1035245 (C4 (Web Text))

Max Activating Token Index: 153

Text #14

Max Range: 7.4343. Min Range: -7.4343

Max Act: 6.6584. Min Act: -0.0000

Data Index: 522151 (C4 (Web Text))

Max Activating Token Index: 629

Text #15

Max Range: 7.4343. Min Range: -7.4343

Max Act: 6.8025. Min Act: -0.0000

Data Index: 247133 (C4 (Web Text))

Max Activating Token Index: 585

Text #16

Max Range: 7.4343. Min Range: -7.4343

Max Act: 6.5752. Min Act: -0.0000

Data Index: 842803 (C4 (Web Text))

Max Activating Token Index: 329

Text #17

Max Range: 7.4343. Min Range: -7.4343

Max Act: 6.7622. Min Act: -0.0000

Data Index: 1325777 (C4 (Web Text))

Max Activating Token Index: 463

Text #18

Max Range: 7.4343. Min Range: -7.4343

Max Act: 6.5751. Min Act: -0.0000

Data Index: 147142 (C4 (Web Text))

Max Activating Token Index: 29

Text #19

Max Range: 7.4343. Min Range: -7.4343

Max Act: 6.8982. Min Act: -0.0000

Data Index: 1063265 (C4 (Web Text))

Max Activating Token Index: 423