Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1582 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.7390. Min Range: -3.7390

Max Act: 3.7390. Min Act: -0.1700

Data Index: 856682 (C4 (Web Text))

Max Activating Token Index: 849

Text #1

Max Range: 3.7390. Min Range: -3.7390

Max Act: 3.7077. Min Act: -0.1700

Data Index: 169490 (C4 (Web Text))

Max Activating Token Index: 761

Text #2

Max Range: 3.7390. Min Range: -3.7390

Max Act: 3.7390. Min Act: -0.1700

Data Index: 942173 (C4 (Web Text))

Max Activating Token Index: 385

Text #3

Max Range: 3.7390. Min Range: -3.7390

Max Act: 3.6764. Min Act: -0.1700

Data Index: 488565 (C4 (Web Text))

Max Activating Token Index: 107

Text #4

Max Range: 3.7390. Min Range: -3.7390

Max Act: 3.7390. Min Act: -0.1700

Data Index: 451641 (C4 (Web Text))

Max Activating Token Index: 896

Text #5

Max Range: 3.7390. Min Range: -3.7390

Max Act: 3.6138. Min Act: -0.1700

Data Index: 882248 (C4 (Web Text))

Max Activating Token Index: 722

Text #6

Max Range: 3.7390. Min Range: -3.7390

Max Act: 3.6451. Min Act: -0.1700

Data Index: 952489 (C4 (Web Text))

Max Activating Token Index: 619

Text #7

Max Range: 3.7390. Min Range: -3.7390

Max Act: 3.6138. Min Act: -0.1700

Data Index: 806676 (C4 (Web Text))

Max Activating Token Index: 783

Text #8

Max Range: 3.7390. Min Range: -3.7390

Max Act: 3.5825. Min Act: -0.1700

Data Index: 333651 (C4 (Web Text))

Max Activating Token Index: 180

Text #9

Max Range: 3.7390. Min Range: -3.7390

Max Act: 3.6138. Min Act: -0.1700

Data Index: 26310 (C4 (Web Text))

Max Activating Token Index: 661

Text #10

Max Range: 3.7390. Min Range: -3.7390

Max Act: 3.6138. Min Act: -0.1700

Data Index: 926204 (C4 (Web Text))

Max Activating Token Index: 839

Text #11

Max Range: 3.7390. Min Range: -3.7390

Max Act: 3.5825. Min Act: -0.1700

Data Index: 1083192 (C4 (Web Text))

Max Activating Token Index: 115

Text #12

Max Range: 3.7390. Min Range: -3.7390

Max Act: 3.5825. Min Act: -0.1700

Data Index: 402486 (C4 (Web Text))

Max Activating Token Index: 764

Text #13

Max Range: 3.7390. Min Range: -3.7390

Max Act: 3.6138. Min Act: -0.1700

Data Index: 377817 (C4 (Web Text))

Max Activating Token Index: 312

Text #14

Max Range: 3.7390. Min Range: -3.7390

Max Act: 3.5512. Min Act: -0.1700

Data Index: 598739 (C4 (Web Text))

Max Activating Token Index: 478

Text #15

Max Range: 3.7390. Min Range: -3.7390

Max Act: 3.5198. Min Act: -0.1700

Data Index: 636076 (C4 (Web Text))

Max Activating Token Index: 437

Text #16

Max Range: 3.7390. Min Range: -3.7390

Max Act: 3.5512. Min Act: -0.1700

Data Index: 785034 (C4 (Web Text))

Max Activating Token Index: 56

Text #17

Max Range: 3.7390. Min Range: -3.7390

Max Act: 3.5825. Min Act: -0.1700

Data Index: 787110 (C4 (Web Text))

Max Activating Token Index: 96

Text #18

Max Range: 3.7390. Min Range: -3.7390

Max Act: 3.4885. Min Act: -0.1700

Data Index: 275968 (C4 (Web Text))

Max Activating Token Index: 665

Text #19

Max Range: 3.7390. Min Range: -3.7390

Max Act: 3.5825. Min Act: -0.1700

Data Index: 860947 (C4 (Web Text))

Max Activating Token Index: 889