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

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

Neuron 1535 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: 3.8082. Min Range: -3.8082

Max Act: 3.8082. Min Act: -0.1700

Data Index: 560925 (C4 (Web Text))

Max Activating Token Index: 79

Text #1

Max Range: 3.8082. Min Range: -3.8082

Max Act: 3.7815. Min Act: -0.1700

Data Index: 73397 (C4 (Web Text))

Max Activating Token Index: 229

Text #2

Max Range: 3.8082. Min Range: -3.8082

Max Act: 3.7696. Min Act: -0.1700

Data Index: 400823 (C4 (Web Text))

Max Activating Token Index: 515

Text #3

Max Range: 3.8082. Min Range: -3.8082

Max Act: 3.7617. Min Act: -0.1700

Data Index: 29006 (C4 (Web Text))

Max Activating Token Index: 339

Text #4

Max Range: 3.8082. Min Range: -3.8082

Max Act: 3.7409. Min Act: -0.1700

Data Index: 395901 (C4 (Web Text))

Max Activating Token Index: 28

Text #5

Max Range: 3.8082. Min Range: -3.8082

Max Act: 3.7141. Min Act: -0.1700

Data Index: 727398 (C4 (Web Text))

Max Activating Token Index: 83

Text #6

Max Range: 3.8082. Min Range: -3.8082

Max Act: 3.7231. Min Act: -0.1700

Data Index: 482328 (C4 (Web Text))

Max Activating Token Index: 943

Text #7

Max Range: 3.8082. Min Range: -3.8082

Max Act: 3.6949. Min Act: -0.1700

Data Index: 824792 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 3.8082. Min Range: -3.8082

Max Act: 3.7120. Min Act: -0.1700

Data Index: 1221167 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 3.8082. Min Range: -3.8082

Max Act: 3.6903. Min Act: -0.1700

Data Index: 929592 (C4 (Web Text))

Max Activating Token Index: 919

Text #10

Max Range: 3.8082. Min Range: -3.8082

Max Act: 3.6988. Min Act: -0.1700

Data Index: 579612 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 3.8082. Min Range: -3.8082

Max Act: 3.7004. Min Act: -0.1700

Data Index: 268201 (C4 (Web Text))

Max Activating Token Index: 436

Text #12

Max Range: 3.8082. Min Range: -3.8082

Max Act: 3.6814. Min Act: -0.1700

Data Index: 837827 (C4 (Web Text))

Max Activating Token Index: 66

Text #13

Max Range: 3.8082. Min Range: -3.8082

Max Act: 3.7022. Min Act: -0.1700

Data Index: 371522 (C4 (Web Text))

Max Activating Token Index: 413

Text #14

Max Range: 3.8082. Min Range: -3.8082

Max Act: 3.6656. Min Act: -0.1700

Data Index: 295630 (C4 (Web Text))

Max Activating Token Index: 399

Text #15

Max Range: 3.8082. Min Range: -3.8082

Max Act: 3.6706. Min Act: -0.1700

Data Index: 91292 (C4 (Web Text))

Max Activating Token Index: 701

Text #16

Max Range: 3.8082. Min Range: -3.8082

Max Act: 3.6604. Min Act: -0.1700

Data Index: 178244 (C4 (Web Text))

Max Activating Token Index: 633

Text #17

Max Range: 3.8082. Min Range: -3.8082

Max Act: 3.6626. Min Act: -0.1700

Data Index: 1283531 (C4 (Web Text))

Max Activating Token Index: 770

Text #18

Max Range: 3.8082. Min Range: -3.8082

Max Act: 3.6656. Min Act: -0.1700

Data Index: 986081 (C4 (Web Text))

Max Activating Token Index: 156

Text #19

Max Range: 3.8082. Min Range: -3.8082

Max Act: 3.6779. Min Act: -0.1700

Data Index: 36202 (C4 (Web Text))

Max Activating Token Index: 382