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

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

Neuron 1041 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: 0.3071. Min Range: -0.3071

Max Act: 0.3071. Min Act: -0.0001

Data Index: 210746 (C4 (Web Text))

Max Activating Token Index: 197

Text #1

Max Range: 0.3071. Min Range: -0.3071

Max Act: 0.2839. Min Act: -0.0000

Data Index: 493742 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 0.3071. Min Range: -0.3071

Max Act: 0.2991. Min Act: -0.0001

Data Index: 278258 (C4 (Web Text))

Max Activating Token Index: 944

Text #3

Max Range: 0.3071. Min Range: -0.3071

Max Act: 0.2571. Min Act: -0.0001

Data Index: 1137941 (C4 (Web Text))

Max Activating Token Index: 881

Text #4

Max Range: 0.3071. Min Range: -0.3071

Max Act: 0.2420. Min Act: -0.0000

Data Index: 1092817 (C4 (Web Text))

Max Activating Token Index: 835

Text #5

Max Range: 0.3071. Min Range: -0.3071

Max Act: 0.2509. Min Act: -0.0001

Data Index: 1135113 (C4 (Web Text))

Max Activating Token Index: 681

Text #6

Max Range: 0.3071. Min Range: -0.3071

Max Act: 0.2701. Min Act: -0.0001

Data Index: 43005 (C4 (Web Text))

Max Activating Token Index: 192

Text #7

Max Range: 0.3071. Min Range: -0.3071

Max Act: 0.2439. Min Act: -0.0000

Data Index: 590707 (C4 (Web Text))

Max Activating Token Index: 316

Text #8

Max Range: 0.3071. Min Range: -0.3071

Max Act: 0.2574. Min Act: -0.0001

Data Index: 530699 (C4 (Web Text))

Max Activating Token Index: 604

Text #9

Max Range: 0.3071. Min Range: -0.3071

Max Act: 0.2448. Min Act: -0.0000

Data Index: 264804 (C4 (Web Text))

Max Activating Token Index: 154

Text #10

Max Range: 0.3071. Min Range: -0.3071

Max Act: 0.2439. Min Act: -0.0001

Data Index: 758109 (C4 (Web Text))

Max Activating Token Index: 707

Text #11

Max Range: 0.3071. Min Range: -0.3071

Max Act: 0.2528. Min Act: -0.0001

Data Index: 414494 (C4 (Web Text))

Max Activating Token Index: 368

Text #12

Max Range: 0.3071. Min Range: -0.3071

Max Act: 0.2508. Min Act: -0.0001

Data Index: 1277951 (C4 (Web Text))

Max Activating Token Index: 154

Text #13

Max Range: 0.3071. Min Range: -0.3071

Max Act: 0.2500. Min Act: -0.0000

Data Index: 206267 (C4 (Web Text))

Max Activating Token Index: 891

Text #14

Max Range: 0.3071. Min Range: -0.3071

Max Act: 0.2439. Min Act: -0.0001

Data Index: 1245684 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 0.3071. Min Range: -0.3071

Max Act: 0.2495. Min Act: -0.0000

Data Index: 18289 (C4 (Web Text))

Max Activating Token Index: 144

Text #16

Max Range: 0.3071. Min Range: -0.3071

Max Act: 0.2608. Min Act: -0.0001

Data Index: 394416 (C4 (Web Text))

Max Activating Token Index: 849

Text #17

Max Range: 0.3071. Min Range: -0.3071

Max Act: 0.2478. Min Act: -0.0001

Data Index: 1029696 (C4 (Web Text))

Max Activating Token Index: 225

Text #18

Max Range: 0.3071. Min Range: -0.3071

Max Act: 0.2306. Min Act: -0.0001

Data Index: 364685 (C4 (Web Text))

Max Activating Token Index: 699

Text #19

Max Range: 0.3071. Min Range: -0.3071

Max Act: 0.2562. Min Act: -0.0001

Data Index: 763002 (C4 (Web Text))

Max Activating Token Index: 695