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

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

Neuron 5875 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: 3.1942. Min Range: -3.1942

Max Act: 2.9178. Min Act: -0.0000

Data Index: 1451713 (Python Code)

Max Activating Token Index: 976

Text #1

Max Range: 3.1942. Min Range: -3.1942

Max Act: 3.1942. Min Act: -0.0000

Data Index: 1573901 (Python Code)

Max Activating Token Index: 805

Text #2

Max Range: 3.1942. Min Range: -3.1942

Max Act: 3.0754. Min Act: -0.0000

Data Index: 1360316 (Python Code)

Max Activating Token Index: 620

Text #3

Max Range: 3.1942. Min Range: -3.1942

Max Act: 2.7645. Min Act: -0.0000

Data Index: 1392304 (Python Code)

Max Activating Token Index: 430

Text #4

Max Range: 3.1942. Min Range: -3.1942

Max Act: 2.4947. Min Act: -0.0000

Data Index: 1549605 (Python Code)

Max Activating Token Index: 728

Text #5

Max Range: 3.1942. Min Range: -3.1942

Max Act: 2.6059. Min Act: -0.0000

Data Index: 939117 (C4 (Web Text))

Max Activating Token Index: 283

Text #6

Max Range: 3.1942. Min Range: -3.1942

Max Act: 2.4749. Min Act: -0.0000

Data Index: 1563098 (Python Code)

Max Activating Token Index: 857

Text #7

Max Range: 3.1942. Min Range: -3.1942

Max Act: 2.3500. Min Act: -0.0000

Data Index: 1364429 (Python Code)

Max Activating Token Index: 170

Text #8

Max Range: 3.1942. Min Range: -3.1942

Max Act: 2.3183. Min Act: -0.0000

Data Index: 390355 (C4 (Web Text))

Max Activating Token Index: 581

Text #9

Max Range: 3.1942. Min Range: -3.1942

Max Act: 2.1741. Min Act: -0.0000

Data Index: 281175 (C4 (Web Text))

Max Activating Token Index: 332

Text #10

Max Range: 3.1942. Min Range: -3.1942

Max Act: 2.0444. Min Act: -0.0000

Data Index: 1420140 (Python Code)

Max Activating Token Index: 934

Text #11

Max Range: 3.1942. Min Range: -3.1942

Max Act: 2.1462. Min Act: -0.0000

Data Index: 1291907 (C4 (Web Text))

Max Activating Token Index: 834

Text #12

Max Range: 3.1942. Min Range: -3.1942

Max Act: 2.3726. Min Act: -0.0000

Data Index: 634849 (C4 (Web Text))

Max Activating Token Index: 273

Text #13

Max Range: 3.1942. Min Range: -3.1942

Max Act: 2.0729. Min Act: -0.0000

Data Index: 1468558 (Python Code)

Max Activating Token Index: 877

Text #14

Max Range: 3.1942. Min Range: -3.1942

Max Act: 2.0036. Min Act: -0.0000

Data Index: 1440584 (Python Code)

Max Activating Token Index: 134

Text #15

Max Range: 3.1942. Min Range: -3.1942

Max Act: 1.9448. Min Act: -0.0000

Data Index: 1479956 (Python Code)

Max Activating Token Index: 697

Text #16

Max Range: 3.1942. Min Range: -3.1942

Max Act: 1.8301. Min Act: -0.0000

Data Index: 200981 (C4 (Web Text))

Max Activating Token Index: 853

Text #17

Max Range: 3.1942. Min Range: -3.1942

Max Act: 1.9755. Min Act: -0.0000

Data Index: 946288 (C4 (Web Text))

Max Activating Token Index: 885

Text #18

Max Range: 3.1942. Min Range: -3.1942

Max Act: 1.7768. Min Act: -0.0000

Data Index: 719103 (C4 (Web Text))

Max Activating Token Index: 32

Text #19

Max Range: 3.1942. Min Range: -3.1942

Max Act: 1.9040. Min Act: -0.0000

Data Index: 1525566 (Python Code)

Max Activating Token Index: 180