Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1756 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0531. Min Act: -0.0006

Data Index: 1289479 (C4 (Web Text))

Max Activating Token Index: 229

Text #1

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0489. Min Act: -0.0006

Data Index: 1022737 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0493. Min Act: -0.0006

Data Index: 1125020 (C4 (Web Text))

Max Activating Token Index: 762

Text #3

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0490. Min Act: -0.0006

Data Index: 52895 (C4 (Web Text))

Max Activating Token Index: 18

Text #4

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0458. Min Act: -0.0006

Data Index: 622876 (C4 (Web Text))

Max Activating Token Index: 239

Text #5

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0463. Min Act: -0.0006

Data Index: 236431 (C4 (Web Text))

Max Activating Token Index: 18

Text #6

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0455. Min Act: -0.0006

Data Index: 565520 (C4 (Web Text))

Max Activating Token Index: 908

Text #7

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0465. Min Act: -0.0006

Data Index: 470431 (C4 (Web Text))

Max Activating Token Index: 152

Text #8

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0475. Min Act: -0.0006

Data Index: 734145 (C4 (Web Text))

Max Activating Token Index: 130

Text #9

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0445. Min Act: -0.0006

Data Index: 110230 (C4 (Web Text))

Max Activating Token Index: 18

Text #10

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0445. Min Act: -0.0006

Data Index: 583547 (C4 (Web Text))

Max Activating Token Index: 808

Text #11

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0428. Min Act: -0.0006

Data Index: 730846 (C4 (Web Text))

Max Activating Token Index: 267

Text #12

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0437. Min Act: -0.0006

Data Index: 920150 (C4 (Web Text))

Max Activating Token Index: 193

Text #13

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0442. Min Act: -0.0006

Data Index: 928352 (C4 (Web Text))

Max Activating Token Index: 509

Text #14

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0407. Min Act: -0.0006

Data Index: 1036706 (C4 (Web Text))

Max Activating Token Index: 872

Text #15

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0424. Min Act: -0.0006

Data Index: 846589 (C4 (Web Text))

Max Activating Token Index: 14

Text #16

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0424. Min Act: -0.0006

Data Index: 1015457 (C4 (Web Text))

Max Activating Token Index: 962

Text #17

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0419. Min Act: -0.0006

Data Index: 38440 (C4 (Web Text))

Max Activating Token Index: 276

Text #18

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0440. Min Act: -0.0006

Data Index: 476895 (C4 (Web Text))

Max Activating Token Index: 424

Text #19

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0421. Min Act: -0.0006

Data Index: 796472 (C4 (Web Text))

Max Activating Token Index: 204