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

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

Neuron 1762 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9758. Min Range: -4.9758

Max Act: 4.9758. Min Act: -0.0000

Data Index: 545689 (C4 (Web Text))

Max Activating Token Index: 225

Text #1

Max Range: 4.9758. Min Range: -4.9758

Max Act: 4.6079. Min Act: -0.0000

Data Index: 76860 (C4 (Web Text))

Max Activating Token Index: 492

Text #2

Max Range: 4.9758. Min Range: -4.9758

Max Act: 4.2151. Min Act: -0.0000

Data Index: 1020446 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 4.9758. Min Range: -4.9758

Max Act: 4.1150. Min Act: -0.0000

Data Index: 984534 (C4 (Web Text))

Max Activating Token Index: 685

Text #4

Max Range: 4.9758. Min Range: -4.9758

Max Act: 3.8774. Min Act: -0.0000

Data Index: 62794 (C4 (Web Text))

Max Activating Token Index: 836

Text #5

Max Range: 4.9758. Min Range: -4.9758

Max Act: 4.1142. Min Act: -0.0000

Data Index: 504628 (C4 (Web Text))

Max Activating Token Index: 460

Text #6

Max Range: 4.9758. Min Range: -4.9758

Max Act: 3.9306. Min Act: -0.0000

Data Index: 698210 (C4 (Web Text))

Max Activating Token Index: 272

Text #7

Max Range: 4.9758. Min Range: -4.9758

Max Act: 3.2365. Min Act: -0.0000

Data Index: 1242848 (C4 (Web Text))

Max Activating Token Index: 229

Text #8

Max Range: 4.9758. Min Range: -4.9758

Max Act: 4.0001. Min Act: -0.0000

Data Index: 549800 (C4 (Web Text))

Max Activating Token Index: 67

Text #9

Max Range: 4.9758. Min Range: -4.9758

Max Act: 3.7340. Min Act: -0.0000

Data Index: 310468 (C4 (Web Text))

Max Activating Token Index: 34

Text #10

Max Range: 4.9758. Min Range: -4.9758

Max Act: 3.5383. Min Act: -0.0000

Data Index: 495880 (C4 (Web Text))

Max Activating Token Index: 320

Text #11

Max Range: 4.9758. Min Range: -4.9758

Max Act: 3.6544. Min Act: -0.0000

Data Index: 281930 (C4 (Web Text))

Max Activating Token Index: 969

Text #12

Max Range: 4.9758. Min Range: -4.9758

Max Act: 3.6097. Min Act: -0.0000

Data Index: 777897 (C4 (Web Text))

Max Activating Token Index: 439

Text #13

Max Range: 4.9758. Min Range: -4.9758

Max Act: 3.6212. Min Act: -0.0000

Data Index: 89052 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 4.9758. Min Range: -4.9758

Max Act: 3.6106. Min Act: -0.0000

Data Index: 136412 (C4 (Web Text))

Max Activating Token Index: 105

Text #15

Max Range: 4.9758. Min Range: -4.9758

Max Act: 3.3123. Min Act: -0.0000

Data Index: 461770 (C4 (Web Text))

Max Activating Token Index: 565

Text #16

Max Range: 4.9758. Min Range: -4.9758

Max Act: 3.4374. Min Act: -0.0000

Data Index: 574758 (C4 (Web Text))

Max Activating Token Index: 574

Text #17

Max Range: 4.9758. Min Range: -4.9758

Max Act: 3.5932. Min Act: -0.0000

Data Index: 111644 (C4 (Web Text))

Max Activating Token Index: 992

Text #18

Max Range: 4.9758. Min Range: -4.9758

Max Act: 3.4172. Min Act: -0.0000

Data Index: 197133 (C4 (Web Text))

Max Activating Token Index: 454

Text #19

Max Range: 4.9758. Min Range: -4.9758

Max Act: 3.3803. Min Act: -0.0000

Data Index: 196494 (C4 (Web Text))

Max Activating Token Index: 986