Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 542 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.4106. Min Range: -3.4106

Max Act: 3.4106. Min Act: -0.1700

Data Index: 859494 (C4 (Web Text))

Max Activating Token Index: 752

Text #1

Max Range: 3.4106. Min Range: -3.4106

Max Act: 3.4106. Min Act: -0.1700

Data Index: 436141 (C4 (Web Text))

Max Activating Token Index: 304

Text #2

Max Range: 3.4106. Min Range: -3.4106

Max Act: 3.3793. Min Act: -0.1700

Data Index: 1111734 (C4 (Web Text))

Max Activating Token Index: 749

Text #3

Max Range: 3.4106. Min Range: -3.4106

Max Act: 3.3479. Min Act: -0.1700

Data Index: 1015647 (C4 (Web Text))

Max Activating Token Index: 514

Text #4

Max Range: 3.4106. Min Range: -3.4106

Max Act: 3.3793. Min Act: -0.1700

Data Index: 14162 (C4 (Web Text))

Max Activating Token Index: 532

Text #5

Max Range: 3.4106. Min Range: -3.4106

Max Act: 3.3165. Min Act: -0.1700

Data Index: 219831 (C4 (Web Text))

Max Activating Token Index: 181

Text #6

Max Range: 3.4106. Min Range: -3.4106

Max Act: 3.3165. Min Act: -0.1700

Data Index: 311567 (C4 (Web Text))

Max Activating Token Index: 129

Text #7

Max Range: 3.4106. Min Range: -3.4106

Max Act: 3.3479. Min Act: -0.1700

Data Index: 1244500 (C4 (Web Text))

Max Activating Token Index: 523

Text #8

Max Range: 3.4106. Min Range: -3.4106

Max Act: 3.2851. Min Act: -0.1700

Data Index: 1598741 (Python Code)

Max Activating Token Index: 81

Text #9

Max Range: 3.4106. Min Range: -3.4106

Max Act: 3.2222. Min Act: -0.1700

Data Index: 1309204 (C4 (Web Text))

Max Activating Token Index: 654

Text #10

Max Range: 3.4106. Min Range: -3.4106

Max Act: 3.2851. Min Act: -0.1700

Data Index: 374327 (C4 (Web Text))

Max Activating Token Index: 343

Text #11

Max Range: 3.4106. Min Range: -3.4106

Max Act: 3.2222. Min Act: -0.1700

Data Index: 140286 (C4 (Web Text))

Max Activating Token Index: 801

Text #12

Max Range: 3.4106. Min Range: -3.4106

Max Act: 3.3165. Min Act: -0.1700

Data Index: 1258745 (C4 (Web Text))

Max Activating Token Index: 806

Text #13

Max Range: 3.4106. Min Range: -3.4106

Max Act: 3.2536. Min Act: -0.1700

Data Index: 851677 (C4 (Web Text))

Max Activating Token Index: 667

Text #14

Max Range: 3.4106. Min Range: -3.4106

Max Act: 3.2065. Min Act: -0.1700

Data Index: 1347525 (C4 (Web Text))

Max Activating Token Index: 393

Text #15

Max Range: 3.4106. Min Range: -3.4106

Max Act: 3.2536. Min Act: -0.1700

Data Index: 586924 (C4 (Web Text))

Max Activating Token Index: 691

Text #16

Max Range: 3.4106. Min Range: -3.4106

Max Act: 3.1435. Min Act: -0.1700

Data Index: 643206 (C4 (Web Text))

Max Activating Token Index: 442

Text #17

Max Range: 3.4106. Min Range: -3.4106

Max Act: 3.2222. Min Act: -0.1700

Data Index: 931247 (C4 (Web Text))

Max Activating Token Index: 445

Text #18

Max Range: 3.4106. Min Range: -3.4106

Max Act: 3.2065. Min Act: -0.1700

Data Index: 16756 (C4 (Web Text))

Max Activating Token Index: 615

Text #19

Max Range: 3.4106. Min Range: -3.4106

Max Act: 3.2536. Min Act: -0.1700

Data Index: 935921 (C4 (Web Text))

Max Activating Token Index: 10