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

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

Neuron 4524 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5462. Min Range: -2.5462

Max Act: 2.5462. Min Act: -0.0000

Data Index: 1252905 (C4 (Web Text))

Max Activating Token Index: 195

Text #1

Max Range: 2.5462. Min Range: -2.5462

Max Act: 2.1798. Min Act: -0.0000

Data Index: 47238 (C4 (Web Text))

Max Activating Token Index: 205

Text #2

Max Range: 2.5462. Min Range: -2.5462

Max Act: 2.3651. Min Act: -0.0000

Data Index: 935586 (C4 (Web Text))

Max Activating Token Index: 69

Text #3

Max Range: 2.5462. Min Range: -2.5462

Max Act: 2.2102. Min Act: -0.0000

Data Index: 1116442 (C4 (Web Text))

Max Activating Token Index: 959

Text #4

Max Range: 2.5462. Min Range: -2.5462

Max Act: 2.2915. Min Act: -0.0000

Data Index: 1073650 (C4 (Web Text))

Max Activating Token Index: 219

Text #5

Max Range: 2.5462. Min Range: -2.5462

Max Act: 2.0807. Min Act: -0.0000

Data Index: 380670 (C4 (Web Text))

Max Activating Token Index: 201

Text #6

Max Range: 2.5462. Min Range: -2.5462

Max Act: 2.1336. Min Act: -0.0000

Data Index: 540740 (C4 (Web Text))

Max Activating Token Index: 572

Text #7

Max Range: 2.5462. Min Range: -2.5462

Max Act: 2.0477. Min Act: -0.0000

Data Index: 503478 (C4 (Web Text))

Max Activating Token Index: 400

Text #8

Max Range: 2.5462. Min Range: -2.5462

Max Act: 1.9425. Min Act: -0.0000

Data Index: 1006509 (C4 (Web Text))

Max Activating Token Index: 441

Text #9

Max Range: 2.5462. Min Range: -2.5462

Max Act: 2.0253. Min Act: -0.0000

Data Index: 1640808 (Python Code)

Max Activating Token Index: 104

Text #10

Max Range: 2.5462. Min Range: -2.5462

Max Act: 1.9988. Min Act: -0.0000

Data Index: 1150821 (C4 (Web Text))

Max Activating Token Index: 278

Text #11

Max Range: 2.5462. Min Range: -2.5462

Max Act: 1.7913. Min Act: -0.0000

Data Index: 1246673 (C4 (Web Text))

Max Activating Token Index: 927

Text #12

Max Range: 2.5462. Min Range: -2.5462

Max Act: 1.8752. Min Act: -0.0000

Data Index: 147964 (C4 (Web Text))

Max Activating Token Index: 471

Text #13

Max Range: 2.5462. Min Range: -2.5462

Max Act: 1.9705. Min Act: -0.0000

Data Index: 1176108 (C4 (Web Text))

Max Activating Token Index: 328

Text #14

Max Range: 2.5462. Min Range: -2.5462

Max Act: 1.8598. Min Act: -0.0000

Data Index: 168274 (C4 (Web Text))

Max Activating Token Index: 334

Text #15

Max Range: 2.5462. Min Range: -2.5462

Max Act: 1.8614. Min Act: -0.0000

Data Index: 1251754 (C4 (Web Text))

Max Activating Token Index: 283

Text #16

Max Range: 2.5462. Min Range: -2.5462

Max Act: 2.0661. Min Act: -0.0000

Data Index: 899820 (C4 (Web Text))

Max Activating Token Index: 383

Text #17

Max Range: 2.5462. Min Range: -2.5462

Max Act: 1.9532. Min Act: -0.0000

Data Index: 370340 (C4 (Web Text))

Max Activating Token Index: 358

Text #18

Max Range: 2.5462. Min Range: -2.5462

Max Act: 1.9580. Min Act: -0.0000

Data Index: 296080 (C4 (Web Text))

Max Activating Token Index: 699

Text #19

Max Range: 2.5462. Min Range: -2.5462

Max Act: 1.9398. Min Act: -0.0000

Data Index: 629538 (C4 (Web Text))

Max Activating Token Index: 731