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

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

Neuron 1087 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0587. Min Act: -0.0001

Data Index: 49555 (C4 (Web Text))

Max Activating Token Index: 803

Text #1

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0509. Min Act: -0.0001

Data Index: 174299 (C4 (Web Text))

Max Activating Token Index: 843

Text #2

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0412. Min Act: -0.0001

Data Index: 1354540 (C4 (Web Text))

Max Activating Token Index: 904

Text #3

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0479. Min Act: -0.0001

Data Index: 515337 (C4 (Web Text))

Max Activating Token Index: 112

Text #4

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0492. Min Act: -0.0001

Data Index: 159239 (C4 (Web Text))

Max Activating Token Index: 100

Text #5

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0472. Min Act: -0.0001

Data Index: 243683 (C4 (Web Text))

Max Activating Token Index: 671

Text #6

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0464. Min Act: -0.0001

Data Index: 1299224 (C4 (Web Text))

Max Activating Token Index: 44

Text #7

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0455. Min Act: -0.0001

Data Index: 360435 (C4 (Web Text))

Max Activating Token Index: 614

Text #8

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0423. Min Act: -0.0001

Data Index: 469430 (C4 (Web Text))

Max Activating Token Index: 752

Text #9

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0453. Min Act: -0.0001

Data Index: 136609 (C4 (Web Text))

Max Activating Token Index: 470

Text #10

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0452. Min Act: -0.0001

Data Index: 488249 (C4 (Web Text))

Max Activating Token Index: 539

Text #11

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0421. Min Act: -0.0001

Data Index: 763623 (C4 (Web Text))

Max Activating Token Index: 752

Text #12

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0442. Min Act: -0.0001

Data Index: 430386 (C4 (Web Text))

Max Activating Token Index: 444

Text #13

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0428. Min Act: -0.0001

Data Index: 1017052 (C4 (Web Text))

Max Activating Token Index: 380

Text #14

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0457. Min Act: -0.0001

Data Index: 196896 (C4 (Web Text))

Max Activating Token Index: 295

Text #15

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0473. Min Act: -0.0001

Data Index: 953813 (C4 (Web Text))

Max Activating Token Index: 659

Text #16

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0422. Min Act: -0.0001

Data Index: 347916 (C4 (Web Text))

Max Activating Token Index: 62

Text #17

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0437. Min Act: -0.0001

Data Index: 673585 (C4 (Web Text))

Max Activating Token Index: 546

Text #18

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0419. Min Act: -0.0001

Data Index: 1199415 (C4 (Web Text))

Max Activating Token Index: 309

Text #19

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0421. Min Act: -0.0001

Data Index: 333973 (C4 (Web Text))

Max Activating Token Index: 833