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

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

Neuron 407 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: 3.4114. Min Range: -3.4114

Max Act: 3.4114. Min Act: -0.1700

Data Index: 1236166 (C4 (Web Text))

Max Activating Token Index: 360

Text #1

Max Range: 3.4114. Min Range: -3.4114

Max Act: 3.3487. Min Act: -0.1700

Data Index: 1178880 (C4 (Web Text))

Max Activating Token Index: 299

Text #2

Max Range: 3.4114. Min Range: -3.4114

Max Act: 3.3173. Min Act: -0.1700

Data Index: 510857 (C4 (Web Text))

Max Activating Token Index: 451

Text #3

Max Range: 3.4114. Min Range: -3.4114

Max Act: 3.3016. Min Act: -0.1700

Data Index: 145149 (C4 (Web Text))

Max Activating Token Index: 58

Text #4

Max Range: 3.4114. Min Range: -3.4114

Max Act: 3.3016. Min Act: -0.1700

Data Index: 230802 (C4 (Web Text))

Max Activating Token Index: 868

Text #5

Max Range: 3.4114. Min Range: -3.4114

Max Act: 3.2859. Min Act: -0.1700

Data Index: 840292 (C4 (Web Text))

Max Activating Token Index: 440

Text #6

Max Range: 3.4114. Min Range: -3.4114

Max Act: 3.2859. Min Act: -0.1700

Data Index: 43910 (C4 (Web Text))

Max Activating Token Index: 569

Text #7

Max Range: 3.4114. Min Range: -3.4114

Max Act: 3.2859. Min Act: -0.1700

Data Index: 1273150 (C4 (Web Text))

Max Activating Token Index: 530

Text #8

Max Range: 3.4114. Min Range: -3.4114

Max Act: 3.2859. Min Act: -0.1700

Data Index: 475115 (C4 (Web Text))

Max Activating Token Index: 277

Text #9

Max Range: 3.4114. Min Range: -3.4114

Max Act: 3.2859. Min Act: -0.1700

Data Index: 488064 (C4 (Web Text))

Max Activating Token Index: 460

Text #10

Max Range: 3.4114. Min Range: -3.4114

Max Act: 3.2702. Min Act: -0.1700

Data Index: 661427 (C4 (Web Text))

Max Activating Token Index: 759

Text #11

Max Range: 3.4114. Min Range: -3.4114

Max Act: 3.2859. Min Act: -0.1700

Data Index: 1321699 (C4 (Web Text))

Max Activating Token Index: 727

Text #12

Max Range: 3.4114. Min Range: -3.4114

Max Act: 3.2544. Min Act: -0.1700

Data Index: 1326678 (C4 (Web Text))

Max Activating Token Index: 208

Text #13

Max Range: 3.4114. Min Range: -3.4114

Max Act: 3.2544. Min Act: -0.1700

Data Index: 111372 (C4 (Web Text))

Max Activating Token Index: 723

Text #14

Max Range: 3.4114. Min Range: -3.4114

Max Act: 3.2544. Min Act: -0.1700

Data Index: 1304787 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 3.4114. Min Range: -3.4114

Max Act: 3.2544. Min Act: -0.1700

Data Index: 731386 (C4 (Web Text))

Max Activating Token Index: 704

Text #16

Max Range: 3.4114. Min Range: -3.4114

Max Act: 3.2387. Min Act: -0.1700

Data Index: 362466 (C4 (Web Text))

Max Activating Token Index: 661

Text #17

Max Range: 3.4114. Min Range: -3.4114

Max Act: 3.2387. Min Act: -0.1700

Data Index: 619720 (C4 (Web Text))

Max Activating Token Index: 131

Text #18

Max Range: 3.4114. Min Range: -3.4114

Max Act: 3.2544. Min Act: -0.1700

Data Index: 1039738 (C4 (Web Text))

Max Activating Token Index: 396

Text #19

Max Range: 3.4114. Min Range: -3.4114

Max Act: 3.2073. Min Act: -0.1700

Data Index: 1197609 (C4 (Web Text))

Max Activating Token Index: 466