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

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

Neuron 1134 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: 3.6317. Min Range: -3.6317

Max Act: 3.6317. Min Act: -0.1700

Data Index: 382840 (C4 (Web Text))

Max Activating Token Index: 35

Text #1

Max Range: 3.6317. Min Range: -3.6317

Max Act: 3.5791. Min Act: -0.1700

Data Index: 782462 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 3.6317. Min Range: -3.6317

Max Act: 3.5804. Min Act: -0.1700

Data Index: 82148 (C4 (Web Text))

Max Activating Token Index: 539

Text #3

Max Range: 3.6317. Min Range: -3.6317

Max Act: 3.5488. Min Act: -0.1700

Data Index: 287155 (C4 (Web Text))

Max Activating Token Index: 791

Text #4

Max Range: 3.6317. Min Range: -3.6317

Max Act: 3.5321. Min Act: -0.1700

Data Index: 1107667 (C4 (Web Text))

Max Activating Token Index: 857

Text #5

Max Range: 3.6317. Min Range: -3.6317

Max Act: 3.5328. Min Act: -0.1700

Data Index: 479588 (C4 (Web Text))

Max Activating Token Index: 468

Text #6

Max Range: 3.6317. Min Range: -3.6317

Max Act: 3.5322. Min Act: -0.1700

Data Index: 252288 (C4 (Web Text))

Max Activating Token Index: 670

Text #7

Max Range: 3.6317. Min Range: -3.6317

Max Act: 3.5300. Min Act: -0.1700

Data Index: 714942 (C4 (Web Text))

Max Activating Token Index: 357

Text #8

Max Range: 3.6317. Min Range: -3.6317

Max Act: 3.5383. Min Act: -0.1700

Data Index: 1356072 (C4 (Web Text))

Max Activating Token Index: 759

Text #9

Max Range: 3.6317. Min Range: -3.6317

Max Act: 3.4955. Min Act: -0.1700

Data Index: 762242 (C4 (Web Text))

Max Activating Token Index: 1000

Text #10

Max Range: 3.6317. Min Range: -3.6317

Max Act: 3.5036. Min Act: -0.1700

Data Index: 21028 (C4 (Web Text))

Max Activating Token Index: 574

Text #11

Max Range: 3.6317. Min Range: -3.6317

Max Act: 3.5085. Min Act: -0.1700

Data Index: 696061 (C4 (Web Text))

Max Activating Token Index: 596

Text #12

Max Range: 3.6317. Min Range: -3.6317

Max Act: 3.4768. Min Act: -0.1700

Data Index: 727079 (C4 (Web Text))

Max Activating Token Index: 157

Text #13

Max Range: 3.6317. Min Range: -3.6317

Max Act: 3.4882. Min Act: -0.1700

Data Index: 1120799 (C4 (Web Text))

Max Activating Token Index: 485

Text #14

Max Range: 3.6317. Min Range: -3.6317

Max Act: 3.4982. Min Act: -0.1700

Data Index: 1276416 (C4 (Web Text))

Max Activating Token Index: 946

Text #15

Max Range: 3.6317. Min Range: -3.6317

Max Act: 3.4593. Min Act: -0.1700

Data Index: 677434 (C4 (Web Text))

Max Activating Token Index: 277

Text #16

Max Range: 3.6317. Min Range: -3.6317

Max Act: 3.4762. Min Act: -0.1700

Data Index: 941510 (C4 (Web Text))

Max Activating Token Index: 417

Text #17

Max Range: 3.6317. Min Range: -3.6317

Max Act: 3.4475. Min Act: -0.1700

Data Index: 474767 (C4 (Web Text))

Max Activating Token Index: 8

Text #18

Max Range: 3.6317. Min Range: -3.6317

Max Act: 3.4555. Min Act: -0.1700

Data Index: 1037873 (C4 (Web Text))

Max Activating Token Index: 473

Text #19

Max Range: 3.6317. Min Range: -3.6317

Max Act: 3.4524. Min Act: -0.1700

Data Index: 633271 (C4 (Web Text))

Max Activating Token Index: 804