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

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

Neuron 571 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5962. Min Range: -3.5962

Max Act: 3.5492. Min Act: -0.1700

Data Index: 628981 (C4 (Web Text))

Max Activating Token Index: 614

Text #1

Max Range: 3.5962. Min Range: -3.5962

Max Act: 3.5962. Min Act: -0.1700

Data Index: 1218573 (C4 (Web Text))

Max Activating Token Index: 678

Text #2

Max Range: 3.5962. Min Range: -3.5962

Max Act: 3.5492. Min Act: -0.1700

Data Index: 692996 (C4 (Web Text))

Max Activating Token Index: 233

Text #3

Max Range: 3.5962. Min Range: -3.5962

Max Act: 3.4865. Min Act: -0.1700

Data Index: 357088 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 3.5962. Min Range: -3.5962

Max Act: 3.4865. Min Act: -0.1700

Data Index: 393499 (C4 (Web Text))

Max Activating Token Index: 830

Text #5

Max Range: 3.5962. Min Range: -3.5962

Max Act: 3.5179. Min Act: -0.1700

Data Index: 160725 (C4 (Web Text))

Max Activating Token Index: 911

Text #6

Max Range: 3.5962. Min Range: -3.5962

Max Act: 3.5179. Min Act: -0.1700

Data Index: 168542 (C4 (Web Text))

Max Activating Token Index: 315

Text #7

Max Range: 3.5962. Min Range: -3.5962

Max Act: 3.4709. Min Act: -0.1700

Data Index: 619423 (C4 (Web Text))

Max Activating Token Index: 452

Text #8

Max Range: 3.5962. Min Range: -3.5962

Max Act: 3.5022. Min Act: -0.1700

Data Index: 539142 (C4 (Web Text))

Max Activating Token Index: 674

Text #9

Max Range: 3.5962. Min Range: -3.5962

Max Act: 3.4395. Min Act: -0.1700

Data Index: 386418 (C4 (Web Text))

Max Activating Token Index: 225

Text #10

Max Range: 3.5962. Min Range: -3.5962

Max Act: 3.4238. Min Act: -0.1700

Data Index: 100666 (C4 (Web Text))

Max Activating Token Index: 563

Text #11

Max Range: 3.5962. Min Range: -3.5962

Max Act: 3.4238. Min Act: -0.1700

Data Index: 793114 (C4 (Web Text))

Max Activating Token Index: 169

Text #12

Max Range: 3.5962. Min Range: -3.5962

Max Act: 3.4552. Min Act: -0.1700

Data Index: 1076842 (C4 (Web Text))

Max Activating Token Index: 681

Text #13

Max Range: 3.5962. Min Range: -3.5962

Max Act: 3.4552. Min Act: -0.1700

Data Index: 148482 (C4 (Web Text))

Max Activating Token Index: 170

Text #14

Max Range: 3.5962. Min Range: -3.5962

Max Act: 3.3611. Min Act: -0.1700

Data Index: 545755 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 3.5962. Min Range: -3.5962

Max Act: 3.3925. Min Act: -0.1700

Data Index: 792795 (C4 (Web Text))

Max Activating Token Index: 402

Text #16

Max Range: 3.5962. Min Range: -3.5962

Max Act: 3.3925. Min Act: -0.1700

Data Index: 642338 (C4 (Web Text))

Max Activating Token Index: 603

Text #17

Max Range: 3.5962. Min Range: -3.5962

Max Act: 3.4082. Min Act: -0.1700

Data Index: 1181184 (C4 (Web Text))

Max Activating Token Index: 473

Text #18

Max Range: 3.5962. Min Range: -3.5962

Max Act: 3.4238. Min Act: -0.1700

Data Index: 552592 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 3.5962. Min Range: -3.5962

Max Act: 3.4552. Min Act: -0.1700

Data Index: 132188 (C4 (Web Text))

Max Activating Token Index: 602