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

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

Neuron 553 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9740. Min Range: -2.9740

Max Act: 2.9740. Min Act: -0.0000

Data Index: 705476 (C4 (Web Text))

Max Activating Token Index: 358

Text #1

Max Range: 2.9740. Min Range: -2.9740

Max Act: 2.1249. Min Act: -0.0000

Data Index: 871723 (C4 (Web Text))

Max Activating Token Index: 887

Text #2

Max Range: 2.9740. Min Range: -2.9740

Max Act: 2.0449. Min Act: -0.0000

Data Index: 846663 (C4 (Web Text))

Max Activating Token Index: 637

Text #3

Max Range: 2.9740. Min Range: -2.9740

Max Act: 1.9944. Min Act: -0.0000

Data Index: 608053 (C4 (Web Text))

Max Activating Token Index: 878

Text #4

Max Range: 2.9740. Min Range: -2.9740

Max Act: 1.9463. Min Act: -0.0000

Data Index: 819781 (C4 (Web Text))

Max Activating Token Index: 87

Text #5

Max Range: 2.9740. Min Range: -2.9740

Max Act: 1.9480. Min Act: -0.0000

Data Index: 531875 (C4 (Web Text))

Max Activating Token Index: 973

Text #6

Max Range: 2.9740. Min Range: -2.9740

Max Act: 1.8942. Min Act: -0.0000

Data Index: 1293210 (C4 (Web Text))

Max Activating Token Index: 864

Text #7

Max Range: 2.9740. Min Range: -2.9740

Max Act: 1.7735. Min Act: -0.0000

Data Index: 1341090 (C4 (Web Text))

Max Activating Token Index: 22

Text #8

Max Range: 2.9740. Min Range: -2.9740

Max Act: 1.8533. Min Act: -0.0000

Data Index: 520987 (C4 (Web Text))

Max Activating Token Index: 907

Text #9

Max Range: 2.9740. Min Range: -2.9740

Max Act: 1.8489. Min Act: -0.0000

Data Index: 989719 (C4 (Web Text))

Max Activating Token Index: 358

Text #10

Max Range: 2.9740. Min Range: -2.9740

Max Act: 1.8511. Min Act: -0.0000

Data Index: 710979 (C4 (Web Text))

Max Activating Token Index: 670

Text #11

Max Range: 2.9740. Min Range: -2.9740

Max Act: 1.8235. Min Act: -0.0000

Data Index: 5720 (C4 (Web Text))

Max Activating Token Index: 431

Text #12

Max Range: 2.9740. Min Range: -2.9740

Max Act: 1.7411. Min Act: -0.0000

Data Index: 1242393 (C4 (Web Text))

Max Activating Token Index: 449

Text #13

Max Range: 2.9740. Min Range: -2.9740

Max Act: 1.8426. Min Act: -0.0000

Data Index: 852271 (C4 (Web Text))

Max Activating Token Index: 269

Text #14

Max Range: 2.9740. Min Range: -2.9740

Max Act: 1.6858. Min Act: -0.0000

Data Index: 275154 (C4 (Web Text))

Max Activating Token Index: 106

Text #15

Max Range: 2.9740. Min Range: -2.9740

Max Act: 1.7462. Min Act: -0.0000

Data Index: 502421 (C4 (Web Text))

Max Activating Token Index: 663

Text #16

Max Range: 2.9740. Min Range: -2.9740

Max Act: 1.5380. Min Act: -0.0000

Data Index: 1280351 (C4 (Web Text))

Max Activating Token Index: 377

Text #17

Max Range: 2.9740. Min Range: -2.9740

Max Act: 1.6314. Min Act: -0.0000

Data Index: 304088 (C4 (Web Text))

Max Activating Token Index: 855

Text #18

Max Range: 2.9740. Min Range: -2.9740

Max Act: 1.6192. Min Act: -0.0000

Data Index: 210070 (C4 (Web Text))

Max Activating Token Index: 931

Text #19

Max Range: 2.9740. Min Range: -2.9740

Max Act: 1.5971. Min Act: -0.0000

Data Index: 1072500 (C4 (Web Text))

Max Activating Token Index: 343