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

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

Neuron 367 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.8409. Min Range: -3.8409

Max Act: 3.8409. Min Act: -0.0000

Data Index: 579144 (C4 (Web Text))

Max Activating Token Index: 721

Text #1

Max Range: 3.8409. Min Range: -3.8409

Max Act: 3.2535. Min Act: -0.0000

Data Index: 1343591 (C4 (Web Text))

Max Activating Token Index: 942

Text #2

Max Range: 3.8409. Min Range: -3.8409

Max Act: 3.0189. Min Act: -0.0000

Data Index: 62115 (C4 (Web Text))

Max Activating Token Index: 427

Text #3

Max Range: 3.8409. Min Range: -3.8409

Max Act: 3.6058. Min Act: -0.0000

Data Index: 669768 (C4 (Web Text))

Max Activating Token Index: 923

Text #4

Max Range: 3.8409. Min Range: -3.8409

Max Act: 2.8749. Min Act: -0.0000

Data Index: 122676 (C4 (Web Text))

Max Activating Token Index: 628

Text #5

Max Range: 3.8409. Min Range: -3.8409

Max Act: 2.7826. Min Act: -0.0000

Data Index: 1055698 (C4 (Web Text))

Max Activating Token Index: 395

Text #6

Max Range: 3.8409. Min Range: -3.8409

Max Act: 3.0549. Min Act: -0.0000

Data Index: 954576 (C4 (Web Text))

Max Activating Token Index: 530

Text #7

Max Range: 3.8409. Min Range: -3.8409

Max Act: 3.0345. Min Act: -0.0000

Data Index: 231523 (C4 (Web Text))

Max Activating Token Index: 922

Text #8

Max Range: 3.8409. Min Range: -3.8409

Max Act: 3.0249. Min Act: -0.0000

Data Index: 597228 (C4 (Web Text))

Max Activating Token Index: 797

Text #9

Max Range: 3.8409. Min Range: -3.8409

Max Act: 2.7242. Min Act: -0.0000

Data Index: 828746 (C4 (Web Text))

Max Activating Token Index: 330

Text #10

Max Range: 3.8409. Min Range: -3.8409

Max Act: 2.5581. Min Act: -0.0000

Data Index: 820606 (C4 (Web Text))

Max Activating Token Index: 909

Text #11

Max Range: 3.8409. Min Range: -3.8409

Max Act: 2.5469. Min Act: -0.0000

Data Index: 464123 (C4 (Web Text))

Max Activating Token Index: 734

Text #12

Max Range: 3.8409. Min Range: -3.8409

Max Act: 2.6593. Min Act: -0.0000

Data Index: 500 (C4 (Web Text))

Max Activating Token Index: 591

Text #13

Max Range: 3.8409. Min Range: -3.8409

Max Act: 2.6507. Min Act: -0.0000

Data Index: 1350805 (C4 (Web Text))

Max Activating Token Index: 435

Text #14

Max Range: 3.8409. Min Range: -3.8409

Max Act: 2.6308. Min Act: -0.0000

Data Index: 1344186 (C4 (Web Text))

Max Activating Token Index: 245

Text #15

Max Range: 3.8409. Min Range: -3.8409

Max Act: 2.4345. Min Act: -0.0000

Data Index: 1105728 (C4 (Web Text))

Max Activating Token Index: 790

Text #16

Max Range: 3.8409. Min Range: -3.8409

Max Act: 2.8202. Min Act: -0.0000

Data Index: 1288661 (C4 (Web Text))

Max Activating Token Index: 387

Text #17

Max Range: 3.8409. Min Range: -3.8409

Max Act: 2.8864. Min Act: -0.0000

Data Index: 1028129 (C4 (Web Text))

Max Activating Token Index: 144

Text #18

Max Range: 3.8409. Min Range: -3.8409

Max Act: 2.3603. Min Act: -0.0000

Data Index: 337517 (C4 (Web Text))

Max Activating Token Index: 183

Text #19

Max Range: 3.8409. Min Range: -3.8409

Max Act: 2.3661. Min Act: -0.0000

Data Index: 176186 (C4 (Web Text))

Max Activating Token Index: 985