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

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

Neuron 534 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: 4.1253. Min Range: -4.1253

Max Act: 4.1116. Min Act: -0.1700

Data Index: 390855 (C4 (Web Text))

Max Activating Token Index: 862

Text #1

Max Range: 4.1253. Min Range: -4.1253

Max Act: 4.1253. Min Act: -0.1700

Data Index: 611487 (C4 (Web Text))

Max Activating Token Index: 635

Text #2

Max Range: 4.1253. Min Range: -4.1253

Max Act: 3.9920. Min Act: -0.1700

Data Index: 1541023 (Python Code)

Max Activating Token Index: 154

Text #3

Max Range: 4.1253. Min Range: -4.1253

Max Act: 3.9603. Min Act: -0.1700

Data Index: 127730 (C4 (Web Text))

Max Activating Token Index: 273

Text #4

Max Range: 4.1253. Min Range: -4.1253

Max Act: 3.9708. Min Act: -0.1700

Data Index: 856933 (C4 (Web Text))

Max Activating Token Index: 136

Text #5

Max Range: 4.1253. Min Range: -4.1253

Max Act: 3.9033. Min Act: -0.1700

Data Index: 631791 (C4 (Web Text))

Max Activating Token Index: 483

Text #6

Max Range: 4.1253. Min Range: -4.1253

Max Act: 3.8976. Min Act: -0.1700

Data Index: 449733 (C4 (Web Text))

Max Activating Token Index: 95

Text #7

Max Range: 4.1253. Min Range: -4.1253

Max Act: 3.8620. Min Act: -0.1700

Data Index: 395375 (C4 (Web Text))

Max Activating Token Index: 582

Text #8

Max Range: 4.1253. Min Range: -4.1253

Max Act: 3.8727. Min Act: -0.1700

Data Index: 805902 (C4 (Web Text))

Max Activating Token Index: 561

Text #9

Max Range: 4.1253. Min Range: -4.1253

Max Act: 3.8070. Min Act: -0.1700

Data Index: 748840 (C4 (Web Text))

Max Activating Token Index: 469

Text #10

Max Range: 4.1253. Min Range: -4.1253

Max Act: 3.7860. Min Act: -0.1700

Data Index: 835584 (C4 (Web Text))

Max Activating Token Index: 547

Text #11

Max Range: 4.1253. Min Range: -4.1253

Max Act: 3.7501. Min Act: -0.1700

Data Index: 87579 (C4 (Web Text))

Max Activating Token Index: 860

Text #12

Max Range: 4.1253. Min Range: -4.1253

Max Act: 3.7320. Min Act: -0.1700

Data Index: 1030370 (C4 (Web Text))

Max Activating Token Index: 840

Text #13

Max Range: 4.1253. Min Range: -4.1253

Max Act: 3.7037. Min Act: -0.1700

Data Index: 426676 (C4 (Web Text))

Max Activating Token Index: 68

Text #14

Max Range: 4.1253. Min Range: -4.1253

Max Act: 3.7103. Min Act: -0.1700

Data Index: 580411 (C4 (Web Text))

Max Activating Token Index: 862

Text #15

Max Range: 4.1253. Min Range: -4.1253

Max Act: 3.7126. Min Act: -0.1700

Data Index: 468558 (C4 (Web Text))

Max Activating Token Index: 338

Text #16

Max Range: 4.1253. Min Range: -4.1253

Max Act: 3.7041. Min Act: -0.1700

Data Index: 444574 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 4.1253. Min Range: -4.1253

Max Act: 3.6301. Min Act: -0.1700

Data Index: 1199729 (C4 (Web Text))

Max Activating Token Index: 352

Text #18

Max Range: 4.1253. Min Range: -4.1253

Max Act: 3.6228. Min Act: -0.1700

Data Index: 1001119 (C4 (Web Text))

Max Activating Token Index: 108

Text #19

Max Range: 4.1253. Min Range: -4.1253

Max Act: 3.6459. Min Act: -0.1700

Data Index: 518411 (C4 (Web Text))

Max Activating Token Index: 450