Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2834 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3915. Min Range: -0.3915

Max Act: 0.3722. Min Act: -0.0001

Data Index: 520601 (C4 (Web Text))

Max Activating Token Index: 929

Text #1

Max Range: 0.3915. Min Range: -0.3915

Max Act: 0.3646. Min Act: -0.0001

Data Index: 478369 (C4 (Web Text))

Max Activating Token Index: 665

Text #2

Max Range: 0.3915. Min Range: -0.3915

Max Act: 0.3915. Min Act: -0.0001

Data Index: 988835 (C4 (Web Text))

Max Activating Token Index: 155

Text #3

Max Range: 0.3915. Min Range: -0.3915

Max Act: 0.3863. Min Act: -0.0001

Data Index: 926565 (C4 (Web Text))

Max Activating Token Index: 679

Text #4

Max Range: 0.3915. Min Range: -0.3915

Max Act: 0.3549. Min Act: -0.0001

Data Index: 95759 (C4 (Web Text))

Max Activating Token Index: 905

Text #5

Max Range: 0.3915. Min Range: -0.3915

Max Act: 0.3301. Min Act: -0.0001

Data Index: 234714 (C4 (Web Text))

Max Activating Token Index: 529

Text #6

Max Range: 0.3915. Min Range: -0.3915

Max Act: 0.3345. Min Act: -0.0001

Data Index: 1304219 (C4 (Web Text))

Max Activating Token Index: 570

Text #7

Max Range: 0.3915. Min Range: -0.3915

Max Act: 0.3269. Min Act: -0.0001

Data Index: 911932 (C4 (Web Text))

Max Activating Token Index: 885

Text #8

Max Range: 0.3915. Min Range: -0.3915

Max Act: 0.3278. Min Act: -0.0001

Data Index: 112705 (C4 (Web Text))

Max Activating Token Index: 336

Text #9

Max Range: 0.3915. Min Range: -0.3915

Max Act: 0.3234. Min Act: -0.0001

Data Index: 524466 (C4 (Web Text))

Max Activating Token Index: 194

Text #10

Max Range: 0.3915. Min Range: -0.3915

Max Act: 0.3454. Min Act: -0.0001

Data Index: 312605 (C4 (Web Text))

Max Activating Token Index: 283

Text #11

Max Range: 0.3915. Min Range: -0.3915

Max Act: 0.3268. Min Act: -0.0001

Data Index: 441109 (C4 (Web Text))

Max Activating Token Index: 672

Text #12

Max Range: 0.3915. Min Range: -0.3915

Max Act: 0.2960. Min Act: -0.0001

Data Index: 596302 (C4 (Web Text))

Max Activating Token Index: 931

Text #13

Max Range: 0.3915. Min Range: -0.3915

Max Act: 0.3596. Min Act: -0.0001

Data Index: 1306841 (C4 (Web Text))

Max Activating Token Index: 309

Text #14

Max Range: 0.3915. Min Range: -0.3915

Max Act: 0.3020. Min Act: -0.0001

Data Index: 712064 (C4 (Web Text))

Max Activating Token Index: 717

Text #15

Max Range: 0.3915. Min Range: -0.3915

Max Act: 0.2806. Min Act: -0.0001

Data Index: 195030 (C4 (Web Text))

Max Activating Token Index: 351

Text #16

Max Range: 0.3915. Min Range: -0.3915

Max Act: 0.2876. Min Act: -0.0001

Data Index: 514172 (C4 (Web Text))

Max Activating Token Index: 819

Text #17

Max Range: 0.3915. Min Range: -0.3915

Max Act: 0.2783. Min Act: -0.0001

Data Index: 1027096 (C4 (Web Text))

Max Activating Token Index: 684

Text #18

Max Range: 0.3915. Min Range: -0.3915

Max Act: 0.2740. Min Act: -0.0001

Data Index: 495667 (C4 (Web Text))

Max Activating Token Index: 310

Text #19

Max Range: 0.3915. Min Range: -0.3915

Max Act: 0.2912. Min Act: -0.0001

Data Index: 126376 (C4 (Web Text))

Max Activating Token Index: 925