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

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

Neuron 701 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: 4.0637. Min Range: -4.0637

Max Act: 4.0637. Min Act: -0.1700

Data Index: 790985 (C4 (Web Text))

Max Activating Token Index: 67

Text #1

Max Range: 4.0637. Min Range: -4.0637

Max Act: 4.0283. Min Act: -0.1700

Data Index: 635428 (C4 (Web Text))

Max Activating Token Index: 506

Text #2

Max Range: 4.0637. Min Range: -4.0637

Max Act: 3.9540. Min Act: -0.1700

Data Index: 122410 (C4 (Web Text))

Max Activating Token Index: 381

Text #3

Max Range: 4.0637. Min Range: -4.0637

Max Act: 3.9645. Min Act: -0.1700

Data Index: 689543 (C4 (Web Text))

Max Activating Token Index: 480

Text #4

Max Range: 4.0637. Min Range: -4.0637

Max Act: 3.9240. Min Act: -0.1700

Data Index: 64674 (C4 (Web Text))

Max Activating Token Index: 1016

Text #5

Max Range: 4.0637. Min Range: -4.0637

Max Act: 3.9050. Min Act: -0.1700

Data Index: 1017518 (C4 (Web Text))

Max Activating Token Index: 572

Text #6

Max Range: 4.0637. Min Range: -4.0637

Max Act: 3.9208. Min Act: -0.1700

Data Index: 1011562 (C4 (Web Text))

Max Activating Token Index: 390

Text #7

Max Range: 4.0637. Min Range: -4.0637

Max Act: 3.8721. Min Act: -0.1700

Data Index: 1228920 (C4 (Web Text))

Max Activating Token Index: 302

Text #8

Max Range: 4.0637. Min Range: -4.0637

Max Act: 3.8998. Min Act: -0.1700

Data Index: 359808 (C4 (Web Text))

Max Activating Token Index: 116

Text #9

Max Range: 4.0637. Min Range: -4.0637

Max Act: 3.8964. Min Act: -0.1700

Data Index: 457907 (C4 (Web Text))

Max Activating Token Index: 622

Text #10

Max Range: 4.0637. Min Range: -4.0637

Max Act: 3.8913. Min Act: -0.1700

Data Index: 453330 (C4 (Web Text))

Max Activating Token Index: 955

Text #11

Max Range: 4.0637. Min Range: -4.0637

Max Act: 3.8711. Min Act: -0.1700

Data Index: 996324 (C4 (Web Text))

Max Activating Token Index: 142

Text #12

Max Range: 4.0637. Min Range: -4.0637

Max Act: 3.8460. Min Act: -0.1700

Data Index: 839740 (C4 (Web Text))

Max Activating Token Index: 524

Text #13

Max Range: 4.0637. Min Range: -4.0637

Max Act: 3.8435. Min Act: -0.1700

Data Index: 656046 (C4 (Web Text))

Max Activating Token Index: 988

Text #14

Max Range: 4.0637. Min Range: -4.0637

Max Act: 3.8267. Min Act: -0.1700

Data Index: 985191 (C4 (Web Text))

Max Activating Token Index: 492

Text #15

Max Range: 4.0637. Min Range: -4.0637

Max Act: 3.8180. Min Act: -0.1700

Data Index: 759734 (C4 (Web Text))

Max Activating Token Index: 532

Text #16

Max Range: 4.0637. Min Range: -4.0637

Max Act: 3.8340. Min Act: -0.1700

Data Index: 677100 (C4 (Web Text))

Max Activating Token Index: 523

Text #17

Max Range: 4.0637. Min Range: -4.0637

Max Act: 3.8431. Min Act: -0.1700

Data Index: 707540 (C4 (Web Text))

Max Activating Token Index: 285

Text #18

Max Range: 4.0637. Min Range: -4.0637

Max Act: 3.8338. Min Act: -0.1700

Data Index: 44995 (C4 (Web Text))

Max Activating Token Index: 620

Text #19

Max Range: 4.0637. Min Range: -4.0637

Max Act: 3.8110. Min Act: -0.1700

Data Index: 1093327 (C4 (Web Text))

Max Activating Token Index: 1012