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

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

Neuron 833 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6615. Min Range: -0.6615

Max Act: 0.6491. Min Act: -0.0000

Data Index: 889387 (C4 (Web Text))

Max Activating Token Index: 501

Text #1

Max Range: 0.6615. Min Range: -0.6615

Max Act: 0.6615. Min Act: -0.0001

Data Index: 100348 (C4 (Web Text))

Max Activating Token Index: 951

Text #2

Max Range: 0.6615. Min Range: -0.6615

Max Act: 0.5985. Min Act: -0.0001

Data Index: 901422 (C4 (Web Text))

Max Activating Token Index: 372

Text #3

Max Range: 0.6615. Min Range: -0.6615

Max Act: 0.6301. Min Act: -0.0000

Data Index: 1337220 (C4 (Web Text))

Max Activating Token Index: 206

Text #4

Max Range: 0.6615. Min Range: -0.6615

Max Act: 0.5681. Min Act: -0.0001

Data Index: 684354 (C4 (Web Text))

Max Activating Token Index: 396

Text #5

Max Range: 0.6615. Min Range: -0.6615

Max Act: 0.5600. Min Act: 0.0000

Data Index: 82889 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 0.6615. Min Range: -0.6615

Max Act: 0.5700. Min Act: -0.0000

Data Index: 120083 (C4 (Web Text))

Max Activating Token Index: 646

Text #7

Max Range: 0.6615. Min Range: -0.6615

Max Act: 0.5231. Min Act: -0.0001

Data Index: 23228 (C4 (Web Text))

Max Activating Token Index: 1007

Text #8

Max Range: 0.6615. Min Range: -0.6615

Max Act: 0.5486. Min Act: -0.0000

Data Index: 603638 (C4 (Web Text))

Max Activating Token Index: 597

Text #9

Max Range: 0.6615. Min Range: -0.6615

Max Act: 0.5323. Min Act: -0.0000

Data Index: 963362 (C4 (Web Text))

Max Activating Token Index: 571

Text #10

Max Range: 0.6615. Min Range: -0.6615

Max Act: 0.5506. Min Act: -0.0001

Data Index: 333961 (C4 (Web Text))

Max Activating Token Index: 197

Text #11

Max Range: 0.6615. Min Range: -0.6615

Max Act: 0.5495. Min Act: -0.0000

Data Index: 428744 (C4 (Web Text))

Max Activating Token Index: 947

Text #12

Max Range: 0.6615. Min Range: -0.6615

Max Act: 0.5425. Min Act: -0.0000

Data Index: 508004 (C4 (Web Text))

Max Activating Token Index: 792

Text #13

Max Range: 0.6615. Min Range: -0.6615

Max Act: 0.5348. Min Act: -0.0001

Data Index: 514897 (C4 (Web Text))

Max Activating Token Index: 881

Text #14

Max Range: 0.6615. Min Range: -0.6615

Max Act: 0.5489. Min Act: -0.0000

Data Index: 708282 (C4 (Web Text))

Max Activating Token Index: 873

Text #15

Max Range: 0.6615. Min Range: -0.6615

Max Act: 0.5268. Min Act: -0.0000

Data Index: 244626 (C4 (Web Text))

Max Activating Token Index: 795

Text #16

Max Range: 0.6615. Min Range: -0.6615

Max Act: 0.5142. Min Act: -0.0000

Data Index: 715501 (C4 (Web Text))

Max Activating Token Index: 858

Text #17

Max Range: 0.6615. Min Range: -0.6615

Max Act: 0.5093. Min Act: -0.0000

Data Index: 1092099 (C4 (Web Text))

Max Activating Token Index: 926

Text #18

Max Range: 0.6615. Min Range: -0.6615

Max Act: 0.5240. Min Act: -0.0001

Data Index: 1330064 (C4 (Web Text))

Max Activating Token Index: 116

Text #19

Max Range: 0.6615. Min Range: -0.6615

Max Act: 0.4962. Min Act: 0.0000

Data Index: 233858 (C4 (Web Text))

Max Activating Token Index: 413