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

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

Neuron 4949 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6183. Min Range: -0.6183

Max Act: 0.5851. Min Act: -0.0000

Data Index: 368913 (C4 (Web Text))

Max Activating Token Index: 727

Text #1

Max Range: 0.6183. Min Range: -0.6183

Max Act: 0.6183. Min Act: -0.0000

Data Index: 642687 (C4 (Web Text))

Max Activating Token Index: 78

Text #2

Max Range: 0.6183. Min Range: -0.6183

Max Act: 0.5585. Min Act: -0.0000

Data Index: 1142535 (C4 (Web Text))

Max Activating Token Index: 60

Text #3

Max Range: 0.6183. Min Range: -0.6183

Max Act: 0.5262. Min Act: -0.0000

Data Index: 378698 (C4 (Web Text))

Max Activating Token Index: 974

Text #4

Max Range: 0.6183. Min Range: -0.6183

Max Act: 0.5499. Min Act: -0.0000

Data Index: 623374 (C4 (Web Text))

Max Activating Token Index: 835

Text #5

Max Range: 0.6183. Min Range: -0.6183

Max Act: 0.5394. Min Act: -0.0000

Data Index: 466423 (C4 (Web Text))

Max Activating Token Index: 777

Text #6

Max Range: 0.6183. Min Range: -0.6183

Max Act: 0.4629. Min Act: -0.0000

Data Index: 1205802 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 0.6183. Min Range: -0.6183

Max Act: 0.4665. Min Act: -0.0000

Data Index: 1243053 (C4 (Web Text))

Max Activating Token Index: 201

Text #8

Max Range: 0.6183. Min Range: -0.6183

Max Act: 0.5297. Min Act: -0.0000

Data Index: 153493 (C4 (Web Text))

Max Activating Token Index: 117

Text #9

Max Range: 0.6183. Min Range: -0.6183

Max Act: 0.4965. Min Act: -0.0000

Data Index: 1197435 (C4 (Web Text))

Max Activating Token Index: 255

Text #10

Max Range: 0.6183. Min Range: -0.6183

Max Act: 0.4541. Min Act: -0.0000

Data Index: 1121380 (C4 (Web Text))

Max Activating Token Index: 68

Text #11

Max Range: 0.6183. Min Range: -0.6183

Max Act: 0.4826. Min Act: -0.0000

Data Index: 592186 (C4 (Web Text))

Max Activating Token Index: 520

Text #12

Max Range: 0.6183. Min Range: -0.6183

Max Act: 0.4831. Min Act: -0.0000

Data Index: 746001 (C4 (Web Text))

Max Activating Token Index: 672

Text #13

Max Range: 0.6183. Min Range: -0.6183

Max Act: 0.4605. Min Act: -0.0000

Data Index: 1115152 (C4 (Web Text))

Max Activating Token Index: 574

Text #14

Max Range: 0.6183. Min Range: -0.6183

Max Act: 0.4445. Min Act: -0.0000

Data Index: 383063 (C4 (Web Text))

Max Activating Token Index: 851

Text #15

Max Range: 0.6183. Min Range: -0.6183

Max Act: 0.4636. Min Act: -0.0000

Data Index: 458942 (C4 (Web Text))

Max Activating Token Index: 142

Text #16

Max Range: 0.6183. Min Range: -0.6183

Max Act: 0.4445. Min Act: -0.0000

Data Index: 7319 (C4 (Web Text))

Max Activating Token Index: 454

Text #17

Max Range: 0.6183. Min Range: -0.6183

Max Act: 0.4753. Min Act: -0.0000

Data Index: 775018 (C4 (Web Text))

Max Activating Token Index: 989

Text #18

Max Range: 0.6183. Min Range: -0.6183

Max Act: 0.4431. Min Act: -0.0000

Data Index: 1251114 (C4 (Web Text))

Max Activating Token Index: 510

Text #19

Max Range: 0.6183. Min Range: -0.6183

Max Act: 0.4578. Min Act: -0.0000

Data Index: 948000 (C4 (Web Text))

Max Activating Token Index: 100