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

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

Neuron 5188 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: 6.0061. Min Range: -6.0061

Max Act: 6.0061. Min Act: -0.0000

Data Index: 968364 (C4 (Web Text))

Max Activating Token Index: 123

Text #1

Max Range: 6.0061. Min Range: -6.0061

Max Act: 5.3529. Min Act: -0.0000

Data Index: 195515 (C4 (Web Text))

Max Activating Token Index: 61

Text #2

Max Range: 6.0061. Min Range: -6.0061

Max Act: 5.2653. Min Act: -0.0000

Data Index: 102123 (C4 (Web Text))

Max Activating Token Index: 614

Text #3

Max Range: 6.0061. Min Range: -6.0061

Max Act: 5.1958. Min Act: -0.0000

Data Index: 1200180 (C4 (Web Text))

Max Activating Token Index: 402

Text #4

Max Range: 6.0061. Min Range: -6.0061

Max Act: 4.9425. Min Act: -0.0000

Data Index: 903672 (C4 (Web Text))

Max Activating Token Index: 377

Text #5

Max Range: 6.0061. Min Range: -6.0061

Max Act: 5.1497. Min Act: -0.0000

Data Index: 233020 (C4 (Web Text))

Max Activating Token Index: 208

Text #6

Max Range: 6.0061. Min Range: -6.0061

Max Act: 4.9174. Min Act: -0.0000

Data Index: 280431 (C4 (Web Text))

Max Activating Token Index: 605

Text #7

Max Range: 6.0061. Min Range: -6.0061

Max Act: 4.8863. Min Act: -0.0000

Data Index: 1101706 (C4 (Web Text))

Max Activating Token Index: 367

Text #8

Max Range: 6.0061. Min Range: -6.0061

Max Act: 4.6034. Min Act: -0.0000

Data Index: 539854 (C4 (Web Text))

Max Activating Token Index: 747

Text #9

Max Range: 6.0061. Min Range: -6.0061

Max Act: 4.5832. Min Act: -0.0000

Data Index: 1139671 (C4 (Web Text))

Max Activating Token Index: 254

Text #10

Max Range: 6.0061. Min Range: -6.0061

Max Act: 4.9431. Min Act: -0.0000

Data Index: 441008 (C4 (Web Text))

Max Activating Token Index: 400

Text #11

Max Range: 6.0061. Min Range: -6.0061

Max Act: 4.9167. Min Act: -0.0000

Data Index: 883154 (C4 (Web Text))

Max Activating Token Index: 1004

Text #12

Max Range: 6.0061. Min Range: -6.0061

Max Act: 4.7128. Min Act: -0.0000

Data Index: 569317 (C4 (Web Text))

Max Activating Token Index: 956

Text #13

Max Range: 6.0061. Min Range: -6.0061

Max Act: 4.6981. Min Act: -0.0000

Data Index: 400840 (C4 (Web Text))

Max Activating Token Index: 272

Text #14

Max Range: 6.0061. Min Range: -6.0061

Max Act: 4.6917. Min Act: -0.0000

Data Index: 249123 (C4 (Web Text))

Max Activating Token Index: 551

Text #15

Max Range: 6.0061. Min Range: -6.0061

Max Act: 4.5084. Min Act: -0.0000

Data Index: 996264 (C4 (Web Text))

Max Activating Token Index: 797

Text #16

Max Range: 6.0061. Min Range: -6.0061

Max Act: 4.6539. Min Act: -0.0000

Data Index: 393449 (C4 (Web Text))

Max Activating Token Index: 679

Text #17

Max Range: 6.0061. Min Range: -6.0061

Max Act: 4.4481. Min Act: -0.0000

Data Index: 376426 (C4 (Web Text))

Max Activating Token Index: 20

Text #18

Max Range: 6.0061. Min Range: -6.0061

Max Act: 4.4517. Min Act: -0.0000

Data Index: 1059308 (C4 (Web Text))

Max Activating Token Index: 991

Text #19

Max Range: 6.0061. Min Range: -6.0061

Max Act: 4.8440. Min Act: -0.0000

Data Index: 416635 (C4 (Web Text))

Max Activating Token Index: 1002