Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 318 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.6423. Min Range: -3.6423

Max Act: 3.6423. Min Act: -0.1700

Data Index: 1242566 (C4 (Web Text))

Max Activating Token Index: 424

Text #1

Max Range: 3.6423. Min Range: -3.6423

Max Act: 3.5640. Min Act: -0.1700

Data Index: 1019290 (C4 (Web Text))

Max Activating Token Index: 486

Text #2

Max Range: 3.6423. Min Range: -3.6423

Max Act: 3.5170. Min Act: -0.1700

Data Index: 708240 (C4 (Web Text))

Max Activating Token Index: 979

Text #3

Max Range: 3.6423. Min Range: -3.6423

Max Act: 3.4700. Min Act: -0.1700

Data Index: 576779 (C4 (Web Text))

Max Activating Token Index: 412

Text #4

Max Range: 3.6423. Min Range: -3.6423

Max Act: 3.4857. Min Act: -0.1700

Data Index: 1333716 (C4 (Web Text))

Max Activating Token Index: 497

Text #5

Max Range: 3.6423. Min Range: -3.6423

Max Act: 3.4544. Min Act: -0.1700

Data Index: 454206 (C4 (Web Text))

Max Activating Token Index: 733

Text #6

Max Range: 3.6423. Min Range: -3.6423

Max Act: 3.4387. Min Act: -0.1700

Data Index: 750561 (C4 (Web Text))

Max Activating Token Index: 821

Text #7

Max Range: 3.6423. Min Range: -3.6423

Max Act: 3.4387. Min Act: -0.1700

Data Index: 646102 (C4 (Web Text))

Max Activating Token Index: 826

Text #8

Max Range: 3.6423. Min Range: -3.6423

Max Act: 3.4387. Min Act: -0.1700

Data Index: 936168 (C4 (Web Text))

Max Activating Token Index: 501

Text #9

Max Range: 3.6423. Min Range: -3.6423

Max Act: 3.4387. Min Act: -0.1700

Data Index: 656027 (C4 (Web Text))

Max Activating Token Index: 788

Text #10

Max Range: 3.6423. Min Range: -3.6423

Max Act: 3.4544. Min Act: -0.1700

Data Index: 1279366 (C4 (Web Text))

Max Activating Token Index: 830

Text #11

Max Range: 3.6423. Min Range: -3.6423

Max Act: 3.4387. Min Act: -0.1700

Data Index: 677382 (C4 (Web Text))

Max Activating Token Index: 563

Text #12

Max Range: 3.6423. Min Range: -3.6423

Max Act: 3.4230. Min Act: -0.1700

Data Index: 1098913 (C4 (Web Text))

Max Activating Token Index: 906

Text #13

Max Range: 3.6423. Min Range: -3.6423

Max Act: 3.3916. Min Act: -0.1700

Data Index: 854819 (C4 (Web Text))

Max Activating Token Index: 195

Text #14

Max Range: 3.6423. Min Range: -3.6423

Max Act: 3.3759. Min Act: -0.1700

Data Index: 830919 (C4 (Web Text))

Max Activating Token Index: 916

Text #15

Max Range: 3.6423. Min Range: -3.6423

Max Act: 3.3759. Min Act: -0.1700

Data Index: 84089 (C4 (Web Text))

Max Activating Token Index: 860

Text #16

Max Range: 3.6423. Min Range: -3.6423

Max Act: 3.3916. Min Act: -0.1700

Data Index: 232541 (C4 (Web Text))

Max Activating Token Index: 576

Text #17

Max Range: 3.6423. Min Range: -3.6423

Max Act: 3.3759. Min Act: -0.1700

Data Index: 468260 (C4 (Web Text))

Max Activating Token Index: 463

Text #18

Max Range: 3.6423. Min Range: -3.6423

Max Act: 3.4073. Min Act: -0.1700

Data Index: 290864 (C4 (Web Text))

Max Activating Token Index: 52

Text #19

Max Range: 3.6423. Min Range: -3.6423

Max Act: 3.3603. Min Act: -0.1700

Data Index: 973821 (C4 (Web Text))

Max Activating Token Index: 922