Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1350 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0552. Min Act: -0.0003

Data Index: 113384 (C4 (Web Text))

Max Activating Token Index: 123

Text #1

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0563. Min Act: -0.0003

Data Index: 1490681 (Python Code)

Max Activating Token Index: 176

Text #2

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0599. Min Act: -0.0003

Data Index: 766317 (C4 (Web Text))

Max Activating Token Index: 589

Text #3

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0535. Min Act: -0.0003

Data Index: 224530 (C4 (Web Text))

Max Activating Token Index: 408

Text #4

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0531. Min Act: -0.0003

Data Index: 969116 (C4 (Web Text))

Max Activating Token Index: 842

Text #5

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0502. Min Act: -0.0003

Data Index: 746963 (C4 (Web Text))

Max Activating Token Index: 218

Text #6

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0537. Min Act: -0.0003

Data Index: 1454608 (Python Code)

Max Activating Token Index: 746

Text #7

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0540. Min Act: -0.0003

Data Index: 237845 (C4 (Web Text))

Max Activating Token Index: 145

Text #8

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0485. Min Act: -0.0003

Data Index: 1555233 (Python Code)

Max Activating Token Index: 851

Text #9

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0496. Min Act: -0.0003

Data Index: 370365 (C4 (Web Text))

Max Activating Token Index: 81

Text #10

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0516. Min Act: -0.0003

Data Index: 1336185 (C4 (Web Text))

Max Activating Token Index: 92

Text #11

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0493. Min Act: -0.0003

Data Index: 922140 (C4 (Web Text))

Max Activating Token Index: 333

Text #12

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0489. Min Act: -0.0003

Data Index: 1093329 (C4 (Web Text))

Max Activating Token Index: 216

Text #13

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0469. Min Act: -0.0003

Data Index: 1200628 (C4 (Web Text))

Max Activating Token Index: 244

Text #14

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0504. Min Act: -0.0003

Data Index: 1160985 (C4 (Web Text))

Max Activating Token Index: 283

Text #15

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0491. Min Act: -0.0003

Data Index: 1308087 (C4 (Web Text))

Max Activating Token Index: 472

Text #16

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0486. Min Act: -0.0003

Data Index: 138415 (C4 (Web Text))

Max Activating Token Index: 156

Text #17

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0492. Min Act: -0.0003

Data Index: 39552 (C4 (Web Text))

Max Activating Token Index: 197

Text #18

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0455. Min Act: -0.0003

Data Index: 1389302 (Python Code)

Max Activating Token Index: 63

Text #19

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0529. Min Act: -0.0003

Data Index: 387274 (C4 (Web Text))

Max Activating Token Index: 77