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

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

Neuron 1885 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: 0.0531. Min Range: -0.0531

Max Act: 0.0497. Min Act: -0.0003

Data Index: 381856 (C4 (Web Text))

Max Activating Token Index: 381

Text #1

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0503. Min Act: -0.0003

Data Index: 1579148 (Python Code)

Max Activating Token Index: 268

Text #2

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0531. Min Act: -0.0003

Data Index: 765213 (C4 (Web Text))

Max Activating Token Index: 82

Text #3

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0509. Min Act: -0.0003

Data Index: 1592272 (Python Code)

Max Activating Token Index: 211

Text #4

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0505. Min Act: -0.0003

Data Index: 314109 (C4 (Web Text))

Max Activating Token Index: 1005

Text #5

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0483. Min Act: -0.0003

Data Index: 947865 (C4 (Web Text))

Max Activating Token Index: 120

Text #6

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0500. Min Act: -0.0003

Data Index: 1428606 (Python Code)

Max Activating Token Index: 115

Text #7

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0455. Min Act: -0.0003

Data Index: 1570539 (Python Code)

Max Activating Token Index: 209

Text #8

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0499. Min Act: -0.0003

Data Index: 1648051 (Python Code)

Max Activating Token Index: 111

Text #9

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0480. Min Act: -0.0003

Data Index: 1588880 (Python Code)

Max Activating Token Index: 75

Text #10

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0505. Min Act: -0.0003

Data Index: 281334 (C4 (Web Text))

Max Activating Token Index: 949

Text #11

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0472. Min Act: -0.0003

Data Index: 308478 (C4 (Web Text))

Max Activating Token Index: 448

Text #12

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0473. Min Act: -0.0003

Data Index: 67647 (C4 (Web Text))

Max Activating Token Index: 1000

Text #13

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0467. Min Act: -0.0003

Data Index: 1423584 (Python Code)

Max Activating Token Index: 210

Text #14

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0457. Min Act: -0.0003

Data Index: 1331480 (C4 (Web Text))

Max Activating Token Index: 86

Text #15

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0467. Min Act: -0.0003

Data Index: 1260111 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0431. Min Act: -0.0003

Data Index: 1418100 (Python Code)

Max Activating Token Index: 137

Text #17

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0454. Min Act: -0.0003

Data Index: 44912 (C4 (Web Text))

Max Activating Token Index: 952

Text #18

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0448. Min Act: -0.0003

Data Index: 733489 (C4 (Web Text))

Max Activating Token Index: 342

Text #19

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0450. Min Act: -0.0003

Data Index: 1172961 (C4 (Web Text))

Max Activating Token Index: 783