Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2955 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5962. Min Range: -0.5962

Max Act: 0.5962. Min Act: -0.0000

Data Index: 1082157 (C4 (Web Text))

Max Activating Token Index: 962

Text #1

Max Range: 0.5962. Min Range: -0.5962

Max Act: 0.5335. Min Act: -0.0000

Data Index: 1018677 (C4 (Web Text))

Max Activating Token Index: 105

Text #2

Max Range: 0.5962. Min Range: -0.5962

Max Act: 0.5174. Min Act: -0.0000

Data Index: 891389 (C4 (Web Text))

Max Activating Token Index: 422

Text #3

Max Range: 0.5962. Min Range: -0.5962

Max Act: 0.4942. Min Act: -0.0000

Data Index: 1171395 (C4 (Web Text))

Max Activating Token Index: 140

Text #4

Max Range: 0.5962. Min Range: -0.5962

Max Act: 0.4725. Min Act: -0.0000

Data Index: 788126 (C4 (Web Text))

Max Activating Token Index: 869

Text #5

Max Range: 0.5962. Min Range: -0.5962

Max Act: 0.4455. Min Act: -0.0000

Data Index: 558445 (C4 (Web Text))

Max Activating Token Index: 553

Text #6

Max Range: 0.5962. Min Range: -0.5962

Max Act: 0.4812. Min Act: -0.0000

Data Index: 761619 (C4 (Web Text))

Max Activating Token Index: 310

Text #7

Max Range: 0.5962. Min Range: -0.5962

Max Act: 0.4513. Min Act: -0.0000

Data Index: 324833 (C4 (Web Text))

Max Activating Token Index: 697

Text #8

Max Range: 0.5962. Min Range: -0.5962

Max Act: 0.4510. Min Act: -0.0000

Data Index: 243383 (C4 (Web Text))

Max Activating Token Index: 528

Text #9

Max Range: 0.5962. Min Range: -0.5962

Max Act: 0.4520. Min Act: -0.0000

Data Index: 679170 (C4 (Web Text))

Max Activating Token Index: 253

Text #10

Max Range: 0.5962. Min Range: -0.5962

Max Act: 0.4026. Min Act: -0.0000

Data Index: 933547 (C4 (Web Text))

Max Activating Token Index: 273

Text #11

Max Range: 0.5962. Min Range: -0.5962

Max Act: 0.4277. Min Act: -0.0000

Data Index: 1008369 (C4 (Web Text))

Max Activating Token Index: 300

Text #12

Max Range: 0.5962. Min Range: -0.5962

Max Act: 0.4178. Min Act: -0.0000

Data Index: 764457 (C4 (Web Text))

Max Activating Token Index: 69

Text #13

Max Range: 0.5962. Min Range: -0.5962

Max Act: 0.4131. Min Act: -0.0000

Data Index: 563972 (C4 (Web Text))

Max Activating Token Index: 545

Text #14

Max Range: 0.5962. Min Range: -0.5962

Max Act: 0.4041. Min Act: -0.0000

Data Index: 82871 (C4 (Web Text))

Max Activating Token Index: 826

Text #15

Max Range: 0.5962. Min Range: -0.5962

Max Act: 0.4065. Min Act: -0.0000

Data Index: 408945 (C4 (Web Text))

Max Activating Token Index: 841

Text #16

Max Range: 0.5962. Min Range: -0.5962

Max Act: 0.4055. Min Act: -0.0000

Data Index: 1273890 (C4 (Web Text))

Max Activating Token Index: 975

Text #17

Max Range: 0.5962. Min Range: -0.5962

Max Act: 0.3992. Min Act: -0.0000

Data Index: 608258 (C4 (Web Text))

Max Activating Token Index: 309

Text #18

Max Range: 0.5962. Min Range: -0.5962

Max Act: 0.4149. Min Act: -0.0000

Data Index: 1231106 (C4 (Web Text))

Max Activating Token Index: 770

Text #19

Max Range: 0.5962. Min Range: -0.5962

Max Act: 0.3994. Min Act: -0.0000

Data Index: 273341 (C4 (Web Text))

Max Activating Token Index: 528