Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1634 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.5379. Min Range: -3.5379

Max Act: 3.5379. Min Act: -0.1700

Data Index: 1221595 (C4 (Web Text))

Max Activating Token Index: 165

Text #1

Max Range: 3.5379. Min Range: -3.5379

Max Act: 3.4909. Min Act: -0.1700

Data Index: 559942 (C4 (Web Text))

Max Activating Token Index: 687

Text #2

Max Range: 3.5379. Min Range: -3.5379

Max Act: 3.3811. Min Act: -0.1700

Data Index: 465465 (C4 (Web Text))

Max Activating Token Index: 19

Text #3

Max Range: 3.5379. Min Range: -3.5379

Max Act: 3.3655. Min Act: -0.1700

Data Index: 1306142 (C4 (Web Text))

Max Activating Token Index: 334

Text #4

Max Range: 3.5379. Min Range: -3.5379

Max Act: 3.3655. Min Act: -0.1700

Data Index: 309140 (C4 (Web Text))

Max Activating Token Index: 939

Text #5

Max Range: 3.5379. Min Range: -3.5379

Max Act: 3.3498. Min Act: -0.1700

Data Index: 1321128 (C4 (Web Text))

Max Activating Token Index: 799

Text #6

Max Range: 3.5379. Min Range: -3.5379

Max Act: 3.3498. Min Act: -0.1700

Data Index: 1066753 (C4 (Web Text))

Max Activating Token Index: 101

Text #7

Max Range: 3.5379. Min Range: -3.5379

Max Act: 3.3341. Min Act: -0.1700

Data Index: 144275 (C4 (Web Text))

Max Activating Token Index: 203

Text #8

Max Range: 3.5379. Min Range: -3.5379

Max Act: 3.3184. Min Act: -0.1700

Data Index: 65921 (C4 (Web Text))

Max Activating Token Index: 183

Text #9

Max Range: 3.5379. Min Range: -3.5379

Max Act: 3.3184. Min Act: -0.1700

Data Index: 955731 (C4 (Web Text))

Max Activating Token Index: 688

Text #10

Max Range: 3.5379. Min Range: -3.5379

Max Act: 3.3184. Min Act: -0.1700

Data Index: 751554 (C4 (Web Text))

Max Activating Token Index: 634

Text #11

Max Range: 3.5379. Min Range: -3.5379

Max Act: 3.2870. Min Act: -0.1700

Data Index: 1049429 (C4 (Web Text))

Max Activating Token Index: 738

Text #12

Max Range: 3.5379. Min Range: -3.5379

Max Act: 3.2398. Min Act: -0.1700

Data Index: 1212899 (C4 (Web Text))

Max Activating Token Index: 833

Text #13

Max Range: 3.5379. Min Range: -3.5379

Max Act: 3.2398. Min Act: -0.1700

Data Index: 623530 (C4 (Web Text))

Max Activating Token Index: 184

Text #14

Max Range: 3.5379. Min Range: -3.5379

Max Act: 3.2398. Min Act: -0.1700

Data Index: 789494 (C4 (Web Text))

Max Activating Token Index: 47

Text #15

Max Range: 3.5379. Min Range: -3.5379

Max Act: 3.2241. Min Act: -0.1700

Data Index: 1188984 (C4 (Web Text))

Max Activating Token Index: 487

Text #16

Max Range: 3.5379. Min Range: -3.5379

Max Act: 3.2084. Min Act: -0.1700

Data Index: 399234 (C4 (Web Text))

Max Activating Token Index: 703

Text #17

Max Range: 3.5379. Min Range: -3.5379

Max Act: 3.2084. Min Act: -0.1700

Data Index: 855261 (C4 (Web Text))

Max Activating Token Index: 733

Text #18

Max Range: 3.5379. Min Range: -3.5379

Max Act: 3.2241. Min Act: -0.1700

Data Index: 1150039 (C4 (Web Text))

Max Activating Token Index: 366

Text #19

Max Range: 3.5379. Min Range: -3.5379

Max Act: 3.2084. Min Act: -0.1700

Data Index: 682346 (C4 (Web Text))

Max Activating Token Index: 303