Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 2033 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 2.6561. Min Range: -2.6561

Max Act: 2.6561. Min Act: -0.1699

Data Index: 1185911 (C4 (Web Text))

Max Activating Token Index: 763

Text #1

Max Range: 2.6561. Min Range: -2.6561

Max Act: 2.5832. Min Act: -0.1700

Data Index: 516441 (C4 (Web Text))

Max Activating Token Index: 862

Text #2

Max Range: 2.6561. Min Range: -2.6561

Max Act: 2.5817. Min Act: -0.1700

Data Index: 37127 (C4 (Web Text))

Max Activating Token Index: 375

Text #3

Max Range: 2.6561. Min Range: -2.6561

Max Act: 2.5650. Min Act: -0.1661

Data Index: 245097 (C4 (Web Text))

Max Activating Token Index: 926

Text #4

Max Range: 2.6561. Min Range: -2.6561

Max Act: 2.5541. Min Act: -0.1700

Data Index: 327927 (C4 (Web Text))

Max Activating Token Index: 838

Text #5

Max Range: 2.6561. Min Range: -2.6561

Max Act: 2.5587. Min Act: -0.1700

Data Index: 1267335 (C4 (Web Text))

Max Activating Token Index: 360

Text #6

Max Range: 2.6561. Min Range: -2.6561

Max Act: 2.5461. Min Act: -0.1700

Data Index: 1044527 (C4 (Web Text))

Max Activating Token Index: 836

Text #7

Max Range: 2.6561. Min Range: -2.6561

Max Act: 2.5452. Min Act: -0.1700

Data Index: 434674 (C4 (Web Text))

Max Activating Token Index: 781

Text #8

Max Range: 2.6561. Min Range: -2.6561

Max Act: 2.5462. Min Act: -0.1700

Data Index: 1115115 (C4 (Web Text))

Max Activating Token Index: 785

Text #9

Max Range: 2.6561. Min Range: -2.6561

Max Act: 2.5367. Min Act: -0.1699

Data Index: 796366 (C4 (Web Text))

Max Activating Token Index: 579

Text #10

Max Range: 2.6561. Min Range: -2.6561

Max Act: 2.5272. Min Act: -0.1700

Data Index: 1294413 (C4 (Web Text))

Max Activating Token Index: 453

Text #11

Max Range: 2.6561. Min Range: -2.6561

Max Act: 2.5338. Min Act: -0.1700

Data Index: 443775 (C4 (Web Text))

Max Activating Token Index: 480

Text #12

Max Range: 2.6561. Min Range: -2.6561

Max Act: 2.5151. Min Act: -0.1700

Data Index: 200753 (C4 (Web Text))

Max Activating Token Index: 924

Text #13

Max Range: 2.6561. Min Range: -2.6561

Max Act: 2.5227. Min Act: -0.1700

Data Index: 878080 (C4 (Web Text))

Max Activating Token Index: 764

Text #14

Max Range: 2.6561. Min Range: -2.6561

Max Act: 2.5178. Min Act: -0.1700

Data Index: 573767 (C4 (Web Text))

Max Activating Token Index: 453

Text #15

Max Range: 2.6561. Min Range: -2.6561

Max Act: 2.5056. Min Act: -0.1700

Data Index: 483816 (C4 (Web Text))

Max Activating Token Index: 288

Text #16

Max Range: 2.6561. Min Range: -2.6561

Max Act: 2.4944. Min Act: -0.1700

Data Index: 1156802 (C4 (Web Text))

Max Activating Token Index: 644

Text #17

Max Range: 2.6561. Min Range: -2.6561

Max Act: 2.5038. Min Act: -0.1700

Data Index: 737609 (C4 (Web Text))

Max Activating Token Index: 418

Text #18

Max Range: 2.6561. Min Range: -2.6561

Max Act: 2.5013. Min Act: -0.1699

Data Index: 693167 (C4 (Web Text))

Max Activating Token Index: 323

Text #19

Max Range: 2.6561. Min Range: -2.6561

Max Act: 2.4915. Min Act: -0.1700

Data Index: 1594578 (Python Code)

Max Activating Token Index: 514