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

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

Neuron 5960 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3855. Min Range: -0.3855

Max Act: 0.3840. Min Act: -0.0000

Data Index: 836508 (C4 (Web Text))

Max Activating Token Index: 575

Text #1

Max Range: 0.3855. Min Range: -0.3855

Max Act: 0.3855. Min Act: -0.0000

Data Index: 135941 (C4 (Web Text))

Max Activating Token Index: 931

Text #2

Max Range: 0.3855. Min Range: -0.3855

Max Act: 0.3658. Min Act: -0.0000

Data Index: 439331 (C4 (Web Text))

Max Activating Token Index: 140

Text #3

Max Range: 0.3855. Min Range: -0.3855

Max Act: 0.3456. Min Act: -0.0000

Data Index: 780829 (C4 (Web Text))

Max Activating Token Index: 921

Text #4

Max Range: 0.3855. Min Range: -0.3855

Max Act: 0.3461. Min Act: -0.0000

Data Index: 589118 (C4 (Web Text))

Max Activating Token Index: 807

Text #5

Max Range: 0.3855. Min Range: -0.3855

Max Act: 0.3310. Min Act: -0.0000

Data Index: 197638 (C4 (Web Text))

Max Activating Token Index: 930

Text #6

Max Range: 0.3855. Min Range: -0.3855

Max Act: 0.3298. Min Act: -0.0000

Data Index: 1137481 (C4 (Web Text))

Max Activating Token Index: 367

Text #7

Max Range: 0.3855. Min Range: -0.3855

Max Act: 0.3036. Min Act: -0.0000

Data Index: 1039713 (C4 (Web Text))

Max Activating Token Index: 572

Text #8

Max Range: 0.3855. Min Range: -0.3855

Max Act: 0.3245. Min Act: -0.0000

Data Index: 313870 (C4 (Web Text))

Max Activating Token Index: 837

Text #9

Max Range: 0.3855. Min Range: -0.3855

Max Act: 0.3322. Min Act: -0.0000

Data Index: 442292 (C4 (Web Text))

Max Activating Token Index: 169

Text #10

Max Range: 0.3855. Min Range: -0.3855

Max Act: 0.3234. Min Act: -0.0000

Data Index: 779079 (C4 (Web Text))

Max Activating Token Index: 435

Text #11

Max Range: 0.3855. Min Range: -0.3855

Max Act: 0.3050. Min Act: -0.0000

Data Index: 845495 (C4 (Web Text))

Max Activating Token Index: 965

Text #12

Max Range: 0.3855. Min Range: -0.3855

Max Act: 0.2738. Min Act: -0.0000

Data Index: 232379 (C4 (Web Text))

Max Activating Token Index: 713

Text #13

Max Range: 0.3855. Min Range: -0.3855

Max Act: 0.2835. Min Act: -0.0000

Data Index: 603396 (C4 (Web Text))

Max Activating Token Index: 537

Text #14

Max Range: 0.3855. Min Range: -0.3855

Max Act: 0.2806. Min Act: -0.0000

Data Index: 136798 (C4 (Web Text))

Max Activating Token Index: 80

Text #15

Max Range: 0.3855. Min Range: -0.3855

Max Act: 0.2769. Min Act: -0.0000

Data Index: 431017 (C4 (Web Text))

Max Activating Token Index: 124

Text #16

Max Range: 0.3855. Min Range: -0.3855

Max Act: 0.2862. Min Act: -0.0000

Data Index: 8425 (C4 (Web Text))

Max Activating Token Index: 831

Text #17

Max Range: 0.3855. Min Range: -0.3855

Max Act: 0.2784. Min Act: -0.0000

Data Index: 361509 (C4 (Web Text))

Max Activating Token Index: 516

Text #18

Max Range: 0.3855. Min Range: -0.3855

Max Act: 0.2585. Min Act: -0.0000

Data Index: 818323 (C4 (Web Text))

Max Activating Token Index: 668

Text #19

Max Range: 0.3855. Min Range: -0.3855

Max Act: 0.2593. Min Act: -0.0000

Data Index: 66248 (C4 (Web Text))

Max Activating Token Index: 363