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

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

Neuron 819 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: 3.0114. Min Range: -3.0114

Max Act: 3.0114. Min Act: -0.1700

Data Index: 22320 (C4 (Web Text))

Max Activating Token Index: 449

Text #1

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.8847. Min Act: -0.1700

Data Index: 228893 (C4 (Web Text))

Max Activating Token Index: 455

Text #2

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.8689. Min Act: -0.1700

Data Index: 34317 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.8530. Min Act: -0.1700

Data Index: 1054536 (C4 (Web Text))

Max Activating Token Index: 455

Text #4

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.8530. Min Act: -0.1700

Data Index: 547259 (C4 (Web Text))

Max Activating Token Index: 541

Text #5

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.8530. Min Act: -0.1700

Data Index: 421877 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.8530. Min Act: -0.1700

Data Index: 582329 (C4 (Web Text))

Max Activating Token Index: 697

Text #7

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.8371. Min Act: -0.1700

Data Index: 285739 (C4 (Web Text))

Max Activating Token Index: 123

Text #8

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.8530. Min Act: -0.1700

Data Index: 364541 (C4 (Web Text))

Max Activating Token Index: 527

Text #9

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.8371. Min Act: -0.1700

Data Index: 270542 (C4 (Web Text))

Max Activating Token Index: 741

Text #10

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.8212. Min Act: -0.1700

Data Index: 373769 (C4 (Web Text))

Max Activating Token Index: 892

Text #11

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.8371. Min Act: -0.1700

Data Index: 637972 (C4 (Web Text))

Max Activating Token Index: 202

Text #12

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.8371. Min Act: -0.1700

Data Index: 961718 (C4 (Web Text))

Max Activating Token Index: 46

Text #13

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.7893. Min Act: -0.1700

Data Index: 834297 (C4 (Web Text))

Max Activating Token Index: 705

Text #14

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.8212. Min Act: -0.1700

Data Index: 434830 (C4 (Web Text))

Max Activating Token Index: 587

Text #15

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.8212. Min Act: -0.1700

Data Index: 325169 (C4 (Web Text))

Max Activating Token Index: 473

Text #16

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.8212. Min Act: -0.1700

Data Index: 925938 (C4 (Web Text))

Max Activating Token Index: 93

Text #17

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.8212. Min Act: -0.1700

Data Index: 886633 (C4 (Web Text))

Max Activating Token Index: 613

Text #18

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.8212. Min Act: -0.1700

Data Index: 1138989 (C4 (Web Text))

Max Activating Token Index: 748

Text #19

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.8212. Min Act: -0.1700

Data Index: 999343 (C4 (Web Text))

Max Activating Token Index: 196