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

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

Neuron 1304 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3959. Min Range: -1.3959

Max Act: 1.3959. Min Act: -0.0001

Data Index: 342329 (C4 (Web Text))

Max Activating Token Index: 255

Text #1

Max Range: 1.3959. Min Range: -1.3959

Max Act: 1.1821. Min Act: -0.0001

Data Index: 871695 (C4 (Web Text))

Max Activating Token Index: 491

Text #2

Max Range: 1.3959. Min Range: -1.3959

Max Act: 0.9250. Min Act: -0.0001

Data Index: 1539036 (Python Code)

Max Activating Token Index: 451

Text #3

Max Range: 1.3959. Min Range: -1.3959

Max Act: 0.8241. Min Act: -0.0001

Data Index: 1191673 (C4 (Web Text))

Max Activating Token Index: 356

Text #4

Max Range: 1.3959. Min Range: -1.3959

Max Act: 0.8028. Min Act: -0.0001

Data Index: 864901 (C4 (Web Text))

Max Activating Token Index: 270

Text #5

Max Range: 1.3959. Min Range: -1.3959

Max Act: 0.8402. Min Act: -0.0001

Data Index: 374678 (C4 (Web Text))

Max Activating Token Index: 482

Text #6

Max Range: 1.3959. Min Range: -1.3959

Max Act: 0.8400. Min Act: -0.0001

Data Index: 1046797 (C4 (Web Text))

Max Activating Token Index: 476

Text #7

Max Range: 1.3959. Min Range: -1.3959

Max Act: 0.7769. Min Act: -0.0001

Data Index: 949555 (C4 (Web Text))

Max Activating Token Index: 139

Text #8

Max Range: 1.3959. Min Range: -1.3959

Max Act: 0.7384. Min Act: -0.0001

Data Index: 721659 (C4 (Web Text))

Max Activating Token Index: 138

Text #9

Max Range: 1.3959. Min Range: -1.3959

Max Act: 0.7367. Min Act: -0.0001

Data Index: 100449 (C4 (Web Text))

Max Activating Token Index: 123

Text #10

Max Range: 1.3959. Min Range: -1.3959

Max Act: 0.6809. Min Act: -0.0001

Data Index: 1201423 (C4 (Web Text))

Max Activating Token Index: 122

Text #11

Max Range: 1.3959. Min Range: -1.3959

Max Act: 0.7328. Min Act: -0.0001

Data Index: 719277 (C4 (Web Text))

Max Activating Token Index: 1021

Text #12

Max Range: 1.3959. Min Range: -1.3959

Max Act: 0.7460. Min Act: -0.0001

Data Index: 858113 (C4 (Web Text))

Max Activating Token Index: 871

Text #13

Max Range: 1.3959. Min Range: -1.3959

Max Act: 0.6791. Min Act: -0.0001

Data Index: 256491 (C4 (Web Text))

Max Activating Token Index: 440

Text #14

Max Range: 1.3959. Min Range: -1.3959

Max Act: 0.6691. Min Act: -0.0001

Data Index: 42540 (C4 (Web Text))

Max Activating Token Index: 527

Text #15

Max Range: 1.3959. Min Range: -1.3959

Max Act: 0.6353. Min Act: -0.0001

Data Index: 77073 (C4 (Web Text))

Max Activating Token Index: 642

Text #16

Max Range: 1.3959. Min Range: -1.3959

Max Act: 0.6622. Min Act: -0.0001

Data Index: 849568 (C4 (Web Text))

Max Activating Token Index: 429

Text #17

Max Range: 1.3959. Min Range: -1.3959

Max Act: 0.6475. Min Act: -0.0001

Data Index: 477498 (C4 (Web Text))

Max Activating Token Index: 857

Text #18

Max Range: 1.3959. Min Range: -1.3959

Max Act: 0.6711. Min Act: -0.0001

Data Index: 521208 (C4 (Web Text))

Max Activating Token Index: 149

Text #19

Max Range: 1.3959. Min Range: -1.3959

Max Act: 0.6451. Min Act: -0.0001

Data Index: 931412 (C4 (Web Text))

Max Activating Token Index: 601