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

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

Neuron 1806 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2154. Min Range: -3.2154

Max Act: 3.2154. Min Act: -0.1700

Data Index: 1014978 (C4 (Web Text))

Max Activating Token Index: 443

Text #1

Max Range: 3.2154. Min Range: -3.2154

Max Act: 3.0579. Min Act: -0.1700

Data Index: 893356 (C4 (Web Text))

Max Activating Token Index: 787

Text #2

Max Range: 3.2154. Min Range: -3.2154

Max Act: 3.0421. Min Act: -0.1700

Data Index: 700975 (C4 (Web Text))

Max Activating Token Index: 180

Text #3

Max Range: 3.2154. Min Range: -3.2154

Max Act: 3.0421. Min Act: -0.1700

Data Index: 1535723 (Python Code)

Max Activating Token Index: 156

Text #4

Max Range: 3.2154. Min Range: -3.2154

Max Act: 3.0263. Min Act: -0.1700

Data Index: 1588016 (Python Code)

Max Activating Token Index: 790

Text #5

Max Range: 3.2154. Min Range: -3.2154

Max Act: 2.9789. Min Act: -0.1700

Data Index: 982559 (C4 (Web Text))

Max Activating Token Index: 469

Text #6

Max Range: 3.2154. Min Range: -3.2154

Max Act: 2.9472. Min Act: -0.1700

Data Index: 1357215 (C4 (Web Text))

Max Activating Token Index: 235

Text #7

Max Range: 3.2154. Min Range: -3.2154

Max Act: 2.9155. Min Act: -0.1700

Data Index: 211473 (C4 (Web Text))

Max Activating Token Index: 458

Text #8

Max Range: 3.2154. Min Range: -3.2154

Max Act: 2.8838. Min Act: -0.1700

Data Index: 213422 (C4 (Web Text))

Max Activating Token Index: 488

Text #9

Max Range: 3.2154. Min Range: -3.2154

Max Act: 2.8838. Min Act: -0.1700

Data Index: 1172657 (C4 (Web Text))

Max Activating Token Index: 665

Text #10

Max Range: 3.2154. Min Range: -3.2154

Max Act: 2.8679. Min Act: -0.1700

Data Index: 407973 (C4 (Web Text))

Max Activating Token Index: 459

Text #11

Max Range: 3.2154. Min Range: -3.2154

Max Act: 2.8838. Min Act: -0.1700

Data Index: 1300641 (C4 (Web Text))

Max Activating Token Index: 181

Text #12

Max Range: 3.2154. Min Range: -3.2154

Max Act: 2.8521. Min Act: -0.1700

Data Index: 914121 (C4 (Web Text))

Max Activating Token Index: 803

Text #13

Max Range: 3.2154. Min Range: -3.2154

Max Act: 2.8521. Min Act: -0.1700

Data Index: 183830 (C4 (Web Text))

Max Activating Token Index: 5

Text #14

Max Range: 3.2154. Min Range: -3.2154

Max Act: 2.8679. Min Act: -0.1700

Data Index: 51096 (C4 (Web Text))

Max Activating Token Index: 464

Text #15

Max Range: 3.2154. Min Range: -3.2154

Max Act: 2.8838. Min Act: -0.1700

Data Index: 683964 (C4 (Web Text))

Max Activating Token Index: 618

Text #16

Max Range: 3.2154. Min Range: -3.2154

Max Act: 2.8679. Min Act: -0.1700

Data Index: 1060718 (C4 (Web Text))

Max Activating Token Index: 643

Text #17

Max Range: 3.2154. Min Range: -3.2154

Max Act: 2.8679. Min Act: -0.1700

Data Index: 493782 (C4 (Web Text))

Max Activating Token Index: 98

Text #18

Max Range: 3.2154. Min Range: -3.2154

Max Act: 2.8521. Min Act: -0.1700

Data Index: 720838 (C4 (Web Text))

Max Activating Token Index: 774

Text #19

Max Range: 3.2154. Min Range: -3.2154

Max Act: 2.8521. Min Act: -0.1700

Data Index: 722903 (C4 (Web Text))

Max Activating Token Index: 456