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

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

Neuron 232 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3068. Min Range: -5.3068

Max Act: 5.3068. Min Act: -0.1700

Data Index: 550782 (C4 (Web Text))

Max Activating Token Index: 851

Text #1

Max Range: 5.3068. Min Range: -5.3068

Max Act: 5.2131. Min Act: -0.1700

Data Index: 928415 (C4 (Web Text))

Max Activating Token Index: 476

Text #2

Max Range: 5.3068. Min Range: -5.3068

Max Act: 5.2131. Min Act: -0.1700

Data Index: 458365 (C4 (Web Text))

Max Activating Token Index: 667

Text #3

Max Range: 5.3068. Min Range: -5.3068

Max Act: 5.0881. Min Act: -0.1700

Data Index: 439496 (C4 (Web Text))

Max Activating Token Index: 961

Text #4

Max Range: 5.3068. Min Range: -5.3068

Max Act: 5.0881. Min Act: -0.1700

Data Index: 1090639 (C4 (Web Text))

Max Activating Token Index: 947

Text #5

Max Range: 5.3068. Min Range: -5.3068

Max Act: 5.1193. Min Act: -0.1700

Data Index: 669819 (C4 (Web Text))

Max Activating Token Index: 473

Text #6

Max Range: 5.3068. Min Range: -5.3068

Max Act: 5.0256. Min Act: -0.1700

Data Index: 1073347 (C4 (Web Text))

Max Activating Token Index: 635

Text #7

Max Range: 5.3068. Min Range: -5.3068

Max Act: 5.0256. Min Act: -0.1700

Data Index: 1057677 (C4 (Web Text))

Max Activating Token Index: 122

Text #8

Max Range: 5.3068. Min Range: -5.3068

Max Act: 5.0256. Min Act: -0.1700

Data Index: 641169 (C4 (Web Text))

Max Activating Token Index: 266

Text #9

Max Range: 5.3068. Min Range: -5.3068

Max Act: 5.0256. Min Act: -0.1700

Data Index: 956336 (C4 (Web Text))

Max Activating Token Index: 664

Text #10

Max Range: 5.3068. Min Range: -5.3068

Max Act: 4.9943. Min Act: -0.1700

Data Index: 478447 (C4 (Web Text))

Max Activating Token Index: 510

Text #11

Max Range: 5.3068. Min Range: -5.3068

Max Act: 4.9631. Min Act: -0.1700

Data Index: 1070295 (C4 (Web Text))

Max Activating Token Index: 343

Text #12

Max Range: 5.3068. Min Range: -5.3068

Max Act: 4.9943. Min Act: -0.1700

Data Index: 704459 (C4 (Web Text))

Max Activating Token Index: 532

Text #13

Max Range: 5.3068. Min Range: -5.3068

Max Act: 4.9943. Min Act: -0.1700

Data Index: 1339371 (C4 (Web Text))

Max Activating Token Index: 87

Text #14

Max Range: 5.3068. Min Range: -5.3068

Max Act: 5.0256. Min Act: -0.1700

Data Index: 89735 (C4 (Web Text))

Max Activating Token Index: 284

Text #15

Max Range: 5.3068. Min Range: -5.3068

Max Act: 5.0256. Min Act: -0.1700

Data Index: 1348811 (C4 (Web Text))

Max Activating Token Index: 389

Text #16

Max Range: 5.3068. Min Range: -5.3068

Max Act: 4.9631. Min Act: -0.1700

Data Index: 585313 (C4 (Web Text))

Max Activating Token Index: 878

Text #17

Max Range: 5.3068. Min Range: -5.3068

Max Act: 4.9943. Min Act: -0.1700

Data Index: 1108560 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 5.3068. Min Range: -5.3068

Max Act: 4.9943. Min Act: -0.1700

Data Index: 759185 (C4 (Web Text))

Max Activating Token Index: 957

Text #19

Max Range: 5.3068. Min Range: -5.3068

Max Act: 4.9631. Min Act: -0.1700

Data Index: 699043 (C4 (Web Text))

Max Activating Token Index: 14