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

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

Neuron 297 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.9244. Min Range: -7.9244

Max Act: 7.9244. Min Act: -0.1699

Data Index: 962607 (C4 (Web Text))

Max Activating Token Index: 618

Text #1

Max Range: 7.9244. Min Range: -7.9244

Max Act: 7.6744. Min Act: -0.1699

Data Index: 27505 (C4 (Web Text))

Max Activating Token Index: 775

Text #2

Max Range: 7.9244. Min Range: -7.9244

Max Act: 7.7057. Min Act: -0.1699

Data Index: 650898 (C4 (Web Text))

Max Activating Token Index: 595

Text #3

Max Range: 7.9244. Min Range: -7.9244

Max Act: 7.6744. Min Act: -0.1699

Data Index: 1200903 (C4 (Web Text))

Max Activating Token Index: 341

Text #4

Max Range: 7.9244. Min Range: -7.9244

Max Act: 7.6119. Min Act: -0.1699

Data Index: 654380 (C4 (Web Text))

Max Activating Token Index: 879

Text #5

Max Range: 7.9244. Min Range: -7.9244

Max Act: 7.4869. Min Act: -0.1699

Data Index: 214039 (C4 (Web Text))

Max Activating Token Index: 804

Text #6

Max Range: 7.9244. Min Range: -7.9244

Max Act: 7.5494. Min Act: -0.1699

Data Index: 186450 (C4 (Web Text))

Max Activating Token Index: 696

Text #7

Max Range: 7.9244. Min Range: -7.9244

Max Act: 7.4869. Min Act: -0.1699

Data Index: 1275625 (C4 (Web Text))

Max Activating Token Index: 483

Text #8

Max Range: 7.9244. Min Range: -7.9244

Max Act: 7.4557. Min Act: -0.1699

Data Index: 473906 (C4 (Web Text))

Max Activating Token Index: 964

Text #9

Max Range: 7.9244. Min Range: -7.9244

Max Act: 7.4557. Min Act: -0.1699

Data Index: 718461 (C4 (Web Text))

Max Activating Token Index: 826

Text #10

Max Range: 7.9244. Min Range: -7.9244

Max Act: 7.3932. Min Act: -0.1699

Data Index: 85650 (C4 (Web Text))

Max Activating Token Index: 738

Text #11

Max Range: 7.9244. Min Range: -7.9244

Max Act: 7.2682. Min Act: -0.1699

Data Index: 164940 (C4 (Web Text))

Max Activating Token Index: 217

Text #12

Max Range: 7.9244. Min Range: -7.9244

Max Act: 7.3619. Min Act: -0.1699

Data Index: 832492 (C4 (Web Text))

Max Activating Token Index: 616

Text #13

Max Range: 7.9244. Min Range: -7.9244

Max Act: 7.2994. Min Act: -0.1699

Data Index: 447999 (C4 (Web Text))

Max Activating Token Index: 663

Text #14

Max Range: 7.9244. Min Range: -7.9244

Max Act: 7.3307. Min Act: -0.1699

Data Index: 136884 (C4 (Web Text))

Max Activating Token Index: 792

Text #15

Max Range: 7.9244. Min Range: -7.9244

Max Act: 7.3307. Min Act: -0.1697

Data Index: 208598 (C4 (Web Text))

Max Activating Token Index: 348

Text #16

Max Range: 7.9244. Min Range: -7.9244

Max Act: 7.3307. Min Act: -0.1697

Data Index: 14025 (C4 (Web Text))

Max Activating Token Index: 649

Text #17

Max Range: 7.9244. Min Range: -7.9244

Max Act: 7.2369. Min Act: -0.1699

Data Index: 264096 (C4 (Web Text))

Max Activating Token Index: 138

Text #18

Max Range: 7.9244. Min Range: -7.9244

Max Act: 7.2994. Min Act: -0.1699

Data Index: 647450 (C4 (Web Text))

Max Activating Token Index: 105

Text #19

Max Range: 7.9244. Min Range: -7.9244

Max Act: 7.3307. Min Act: -0.1699

Data Index: 631688 (C4 (Web Text))

Max Activating Token Index: 119