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

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

Neuron 1561 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4371. Min Range: -0.4371

Max Act: 0.4371. Min Act: -0.0000

Data Index: 441835 (C4 (Web Text))

Max Activating Token Index: 941

Text #1

Max Range: 0.4371. Min Range: -0.4371

Max Act: 0.3621. Min Act: -0.0000

Data Index: 866564 (C4 (Web Text))

Max Activating Token Index: 606

Text #2

Max Range: 0.4371. Min Range: -0.4371

Max Act: 0.4150. Min Act: -0.0000

Data Index: 933639 (C4 (Web Text))

Max Activating Token Index: 261

Text #3

Max Range: 0.4371. Min Range: -0.4371

Max Act: 0.4242. Min Act: -0.0000

Data Index: 641667 (C4 (Web Text))

Max Activating Token Index: 1012

Text #4

Max Range: 0.4371. Min Range: -0.4371

Max Act: 0.3705. Min Act: -0.0000

Data Index: 749451 (C4 (Web Text))

Max Activating Token Index: 965

Text #5

Max Range: 0.4371. Min Range: -0.4371

Max Act: 0.3876. Min Act: -0.0000

Data Index: 5074 (C4 (Web Text))

Max Activating Token Index: 232

Text #6

Max Range: 0.4371. Min Range: -0.4371

Max Act: 0.3590. Min Act: -0.0000

Data Index: 238307 (C4 (Web Text))

Max Activating Token Index: 708

Text #7

Max Range: 0.4371. Min Range: -0.4371

Max Act: 0.3707. Min Act: -0.0000

Data Index: 1330327 (C4 (Web Text))

Max Activating Token Index: 869

Text #8

Max Range: 0.4371. Min Range: -0.4371

Max Act: 0.3127. Min Act: -0.0000

Data Index: 487774 (C4 (Web Text))

Max Activating Token Index: 113

Text #9

Max Range: 0.4371. Min Range: -0.4371

Max Act: 0.3085. Min Act: -0.0000

Data Index: 283200 (C4 (Web Text))

Max Activating Token Index: 402

Text #10

Max Range: 0.4371. Min Range: -0.4371

Max Act: 0.3276. Min Act: -0.0000

Data Index: 403989 (C4 (Web Text))

Max Activating Token Index: 122

Text #11

Max Range: 0.4371. Min Range: -0.4371

Max Act: 0.3068. Min Act: -0.0000

Data Index: 1166045 (C4 (Web Text))

Max Activating Token Index: 235

Text #12

Max Range: 0.4371. Min Range: -0.4371

Max Act: 0.3066. Min Act: -0.0000

Data Index: 567644 (C4 (Web Text))

Max Activating Token Index: 855

Text #13

Max Range: 0.4371. Min Range: -0.4371

Max Act: 0.3187. Min Act: -0.0000

Data Index: 1294024 (C4 (Web Text))

Max Activating Token Index: 582

Text #14

Max Range: 0.4371. Min Range: -0.4371

Max Act: 0.3041. Min Act: -0.0000

Data Index: 763803 (C4 (Web Text))

Max Activating Token Index: 528

Text #15

Max Range: 0.4371. Min Range: -0.4371

Max Act: 0.2914. Min Act: -0.0000

Data Index: 784261 (C4 (Web Text))

Max Activating Token Index: 190

Text #16

Max Range: 0.4371. Min Range: -0.4371

Max Act: 0.2970. Min Act: -0.0000

Data Index: 1055083 (C4 (Web Text))

Max Activating Token Index: 695

Text #17

Max Range: 0.4371. Min Range: -0.4371

Max Act: 0.2844. Min Act: -0.0000

Data Index: 1243463 (C4 (Web Text))

Max Activating Token Index: 673

Text #18

Max Range: 0.4371. Min Range: -0.4371

Max Act: 0.2904. Min Act: -0.0000

Data Index: 615435 (C4 (Web Text))

Max Activating Token Index: 596

Text #19

Max Range: 0.4371. Min Range: -0.4371

Max Act: 0.2802. Min Act: -0.0000

Data Index: 2440 (C4 (Web Text))

Max Activating Token Index: 263