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

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

Neuron 356 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7103. Min Range: -4.7103

Max Act: 4.7103. Min Act: -0.0000

Data Index: 1011516 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 4.7103. Min Range: -4.7103

Max Act: 4.1049. Min Act: -0.0000

Data Index: 134501 (C4 (Web Text))

Max Activating Token Index: 475

Text #2

Max Range: 4.7103. Min Range: -4.7103

Max Act: 4.1247. Min Act: -0.0000

Data Index: 1058473 (C4 (Web Text))

Max Activating Token Index: 853

Text #3

Max Range: 4.7103. Min Range: -4.7103

Max Act: 3.8994. Min Act: -0.0000

Data Index: 958942 (C4 (Web Text))

Max Activating Token Index: 948

Text #4

Max Range: 4.7103. Min Range: -4.7103

Max Act: 3.3788. Min Act: -0.0000

Data Index: 807390 (C4 (Web Text))

Max Activating Token Index: 640

Text #5

Max Range: 4.7103. Min Range: -4.7103

Max Act: 3.8638. Min Act: -0.0000

Data Index: 114326 (C4 (Web Text))

Max Activating Token Index: 353

Text #6

Max Range: 4.7103. Min Range: -4.7103

Max Act: 3.8713. Min Act: -0.0000

Data Index: 371850 (C4 (Web Text))

Max Activating Token Index: 756

Text #7

Max Range: 4.7103. Min Range: -4.7103

Max Act: 3.5259. Min Act: -0.0000

Data Index: 974804 (C4 (Web Text))

Max Activating Token Index: 748

Text #8

Max Range: 4.7103. Min Range: -4.7103

Max Act: 3.7965. Min Act: -0.0000

Data Index: 652326 (C4 (Web Text))

Max Activating Token Index: 957

Text #9

Max Range: 4.7103. Min Range: -4.7103

Max Act: 3.5835. Min Act: -0.0000

Data Index: 1271694 (C4 (Web Text))

Max Activating Token Index: 539

Text #10

Max Range: 4.7103. Min Range: -4.7103

Max Act: 3.6488. Min Act: -0.0000

Data Index: 434840 (C4 (Web Text))

Max Activating Token Index: 795

Text #11

Max Range: 4.7103. Min Range: -4.7103

Max Act: 3.6142. Min Act: -0.0000

Data Index: 354124 (C4 (Web Text))

Max Activating Token Index: 852

Text #12

Max Range: 4.7103. Min Range: -4.7103

Max Act: 3.6023. Min Act: -0.0000

Data Index: 234937 (C4 (Web Text))

Max Activating Token Index: 285

Text #13

Max Range: 4.7103. Min Range: -4.7103

Max Act: 3.1313. Min Act: -0.0000

Data Index: 47035 (C4 (Web Text))

Max Activating Token Index: 152

Text #14

Max Range: 4.7103. Min Range: -4.7103

Max Act: 3.4288. Min Act: -0.0000

Data Index: 526602 (C4 (Web Text))

Max Activating Token Index: 527

Text #15

Max Range: 4.7103. Min Range: -4.7103

Max Act: 3.5620. Min Act: -0.0000

Data Index: 717554 (C4 (Web Text))

Max Activating Token Index: 873

Text #16

Max Range: 4.7103. Min Range: -4.7103

Max Act: 3.3966. Min Act: -0.0000

Data Index: 466417 (C4 (Web Text))

Max Activating Token Index: 945

Text #17

Max Range: 4.7103. Min Range: -4.7103

Max Act: 3.0443. Min Act: -0.0000

Data Index: 1266390 (C4 (Web Text))

Max Activating Token Index: 837

Text #18

Max Range: 4.7103. Min Range: -4.7103

Max Act: 3.3239. Min Act: -0.0000

Data Index: 132289 (C4 (Web Text))

Max Activating Token Index: 115

Text #19

Max Range: 4.7103. Min Range: -4.7103

Max Act: 3.1404. Min Act: -0.0000

Data Index: 297930 (C4 (Web Text))

Max Activating Token Index: 380