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

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

Neuron 5758 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9936. Min Range: -0.9936

Max Act: 0.9936. Min Act: -0.0000

Data Index: 787115 (C4 (Web Text))

Max Activating Token Index: 559

Text #1

Max Range: 0.9936. Min Range: -0.9936

Max Act: 0.8876. Min Act: -0.0000

Data Index: 80193 (C4 (Web Text))

Max Activating Token Index: 723

Text #2

Max Range: 0.9936. Min Range: -0.9936

Max Act: 0.8702. Min Act: -0.0000

Data Index: 414100 (C4 (Web Text))

Max Activating Token Index: 534

Text #3

Max Range: 0.9936. Min Range: -0.9936

Max Act: 0.8592. Min Act: -0.0000

Data Index: 1211695 (C4 (Web Text))

Max Activating Token Index: 25

Text #4

Max Range: 0.9936. Min Range: -0.9936

Max Act: 0.8563. Min Act: -0.0000

Data Index: 935826 (C4 (Web Text))

Max Activating Token Index: 82

Text #5

Max Range: 0.9936. Min Range: -0.9936

Max Act: 0.8289. Min Act: 0.0000

Data Index: 1205534 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 0.9936. Min Range: -0.9936

Max Act: 0.7870. Min Act: -0.0000

Data Index: 712951 (C4 (Web Text))

Max Activating Token Index: 666

Text #7

Max Range: 0.9936. Min Range: -0.9936

Max Act: 0.8307. Min Act: -0.0000

Data Index: 709113 (C4 (Web Text))

Max Activating Token Index: 112

Text #8

Max Range: 0.9936. Min Range: -0.9936

Max Act: 0.7586. Min Act: -0.0000

Data Index: 387153 (C4 (Web Text))

Max Activating Token Index: 262

Text #9

Max Range: 0.9936. Min Range: -0.9936

Max Act: 0.7296. Min Act: -0.0000

Data Index: 482207 (C4 (Web Text))

Max Activating Token Index: 829

Text #10

Max Range: 0.9936. Min Range: -0.9936

Max Act: 0.7762. Min Act: 0.0000

Data Index: 994527 (C4 (Web Text))

Max Activating Token Index: 10

Text #11

Max Range: 0.9936. Min Range: -0.9936

Max Act: 0.7535. Min Act: 0.0000

Data Index: 536208 (C4 (Web Text))

Max Activating Token Index: 160

Text #12

Max Range: 0.9936. Min Range: -0.9936

Max Act: 0.7475. Min Act: -0.0000

Data Index: 1345746 (C4 (Web Text))

Max Activating Token Index: 36

Text #13

Max Range: 0.9936. Min Range: -0.9936

Max Act: 0.7413. Min Act: -0.0000

Data Index: 3252 (C4 (Web Text))

Max Activating Token Index: 357

Text #14

Max Range: 0.9936. Min Range: -0.9936

Max Act: 0.7532. Min Act: -0.0000

Data Index: 16096 (C4 (Web Text))

Max Activating Token Index: 1008

Text #15

Max Range: 0.9936. Min Range: -0.9936

Max Act: 0.7401. Min Act: -0.0000

Data Index: 919081 (C4 (Web Text))

Max Activating Token Index: 632

Text #16

Max Range: 0.9936. Min Range: -0.9936

Max Act: 0.7338. Min Act: -0.0000

Data Index: 668093 (C4 (Web Text))

Max Activating Token Index: 727

Text #17

Max Range: 0.9936. Min Range: -0.9936

Max Act: 0.6792. Min Act: -0.0000

Data Index: 173096 (C4 (Web Text))

Max Activating Token Index: 387

Text #18

Max Range: 0.9936. Min Range: -0.9936

Max Act: 0.7125. Min Act: -0.0000

Data Index: 1006620 (C4 (Web Text))

Max Activating Token Index: 126

Text #19

Max Range: 0.9936. Min Range: -0.9936

Max Act: 0.7048. Min Act: -0.0000

Data Index: 46198 (C4 (Web Text))

Max Activating Token Index: 15