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

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

Neuron 4373 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0491. Min Act: -0.0002

Data Index: 242526 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0472. Min Act: -0.0002

Data Index: 320230 (C4 (Web Text))

Max Activating Token Index: 648

Text #2

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0468. Min Act: -0.0002

Data Index: 1233202 (C4 (Web Text))

Max Activating Token Index: 393

Text #3

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0465. Min Act: -0.0002

Data Index: 451531 (C4 (Web Text))

Max Activating Token Index: 149

Text #4

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0473. Min Act: -0.0002

Data Index: 256169 (C4 (Web Text))

Max Activating Token Index: 118

Text #5

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0457. Min Act: -0.0002

Data Index: 672228 (C4 (Web Text))

Max Activating Token Index: 250

Text #6

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0456. Min Act: -0.0002

Data Index: 698820 (C4 (Web Text))

Max Activating Token Index: 67

Text #7

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0455. Min Act: -0.0002

Data Index: 803304 (C4 (Web Text))

Max Activating Token Index: 246

Text #8

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0462. Min Act: -0.0002

Data Index: 965365 (C4 (Web Text))

Max Activating Token Index: 69

Text #9

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0448. Min Act: -0.0002

Data Index: 826278 (C4 (Web Text))

Max Activating Token Index: 23

Text #10

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0445. Min Act: -0.0002

Data Index: 847600 (C4 (Web Text))

Max Activating Token Index: 123

Text #11

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0444. Min Act: -0.0002

Data Index: 921380 (C4 (Web Text))

Max Activating Token Index: 124

Text #12

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0443. Min Act: -0.0002

Data Index: 996705 (C4 (Web Text))

Max Activating Token Index: 233

Text #13

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0442. Min Act: -0.0002

Data Index: 44033 (C4 (Web Text))

Max Activating Token Index: 96

Text #14

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0435. Min Act: -0.0002

Data Index: 1128015 (C4 (Web Text))

Max Activating Token Index: 12

Text #15

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0433. Min Act: -0.0002

Data Index: 8746 (C4 (Web Text))

Max Activating Token Index: 648

Text #16

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0431. Min Act: -0.0002

Data Index: 420219 (C4 (Web Text))

Max Activating Token Index: 266

Text #17

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0431. Min Act: -0.0002

Data Index: 300451 (C4 (Web Text))

Max Activating Token Index: 495

Text #18

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0431. Min Act: -0.0002

Data Index: 455437 (C4 (Web Text))

Max Activating Token Index: 106

Text #19

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0421. Min Act: -0.0002

Data Index: 276906 (C4 (Web Text))

Max Activating Token Index: 61