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

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

Neuron 5798 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0069. Min Range: -1.0069

Max Act: 1.0069. Min Act: 0.0000

Data Index: 459427 (C4 (Web Text))

Max Activating Token Index: 124

Text #1

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.9226. Min Act: -0.0000

Data Index: 1140376 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.7741. Min Act: -0.0000

Data Index: 1300101 (C4 (Web Text))

Max Activating Token Index: 237

Text #3

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.8531. Min Act: -0.0000

Data Index: 855486 (C4 (Web Text))

Max Activating Token Index: 933

Text #4

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.7928. Min Act: -0.0000

Data Index: 667940 (C4 (Web Text))

Max Activating Token Index: 53

Text #5

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.7725. Min Act: -0.0000

Data Index: 741286 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.7471. Min Act: -0.0000

Data Index: 315421 (C4 (Web Text))

Max Activating Token Index: 97

Text #7

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.8137. Min Act: -0.0000

Data Index: 935176 (C4 (Web Text))

Max Activating Token Index: 849

Text #8

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.7592. Min Act: -0.0000

Data Index: 827242 (C4 (Web Text))

Max Activating Token Index: 791

Text #9

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.7881. Min Act: -0.0000

Data Index: 10999 (C4 (Web Text))

Max Activating Token Index: 774

Text #10

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.7348. Min Act: -0.0000

Data Index: 6019 (C4 (Web Text))

Max Activating Token Index: 406

Text #11

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.7068. Min Act: -0.0000

Data Index: 919738 (C4 (Web Text))

Max Activating Token Index: 309

Text #12

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.7506. Min Act: -0.0000

Data Index: 748710 (C4 (Web Text))

Max Activating Token Index: 143

Text #13

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.7465. Min Act: -0.0000

Data Index: 1121988 (C4 (Web Text))

Max Activating Token Index: 657

Text #14

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.6671. Min Act: -0.0000

Data Index: 689841 (C4 (Web Text))

Max Activating Token Index: 826

Text #15

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.6677. Min Act: -0.0000

Data Index: 245153 (C4 (Web Text))

Max Activating Token Index: 661

Text #16

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.6644. Min Act: -0.0000

Data Index: 1226004 (C4 (Web Text))

Max Activating Token Index: 639

Text #17

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.6785. Min Act: -0.0000

Data Index: 205167 (C4 (Web Text))

Max Activating Token Index: 989

Text #18

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.6461. Min Act: -0.0000

Data Index: 603022 (C4 (Web Text))

Max Activating Token Index: 639

Text #19

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.6291. Min Act: -0.0000

Data Index: 1343596 (C4 (Web Text))

Max Activating Token Index: 932