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

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

Neuron 563 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2423. Min Range: -3.2423

Max Act: 3.2423. Min Act: -0.1700

Data Index: 292337 (C4 (Web Text))

Max Activating Token Index: 204

Text #1

Max Range: 3.2423. Min Range: -3.2423

Max Act: 3.1322. Min Act: -0.1700

Data Index: 230506 (C4 (Web Text))

Max Activating Token Index: 90

Text #2

Max Range: 3.2423. Min Range: -3.2423

Max Act: 3.1164. Min Act: -0.1700

Data Index: 526140 (C4 (Web Text))

Max Activating Token Index: 133

Text #3

Max Range: 3.2423. Min Range: -3.2423

Max Act: 3.1007. Min Act: -0.1700

Data Index: 532828 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 3.2423. Min Range: -3.2423

Max Act: 3.1164. Min Act: -0.1700

Data Index: 342048 (C4 (Web Text))

Max Activating Token Index: 652

Text #5

Max Range: 3.2423. Min Range: -3.2423

Max Act: 3.1164. Min Act: -0.1700

Data Index: 463365 (C4 (Web Text))

Max Activating Token Index: 724

Text #6

Max Range: 3.2423. Min Range: -3.2423

Max Act: 3.0849. Min Act: -0.1700

Data Index: 88906 (C4 (Web Text))

Max Activating Token Index: 556

Text #7

Max Range: 3.2423. Min Range: -3.2423

Max Act: 3.0849. Min Act: -0.1700

Data Index: 623313 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 3.2423. Min Range: -3.2423

Max Act: 3.0849. Min Act: -0.1700

Data Index: 418303 (C4 (Web Text))

Max Activating Token Index: 468

Text #9

Max Range: 3.2423. Min Range: -3.2423

Max Act: 3.0849. Min Act: -0.1700

Data Index: 93468 (C4 (Web Text))

Max Activating Token Index: 794

Text #10

Max Range: 3.2423. Min Range: -3.2423

Max Act: 3.1007. Min Act: -0.1700

Data Index: 1181586 (C4 (Web Text))

Max Activating Token Index: 94

Text #11

Max Range: 3.2423. Min Range: -3.2423

Max Act: 3.0691. Min Act: -0.1700

Data Index: 573847 (C4 (Web Text))

Max Activating Token Index: 263

Text #12

Max Range: 3.2423. Min Range: -3.2423

Max Act: 3.0691. Min Act: -0.1700

Data Index: 1092090 (C4 (Web Text))

Max Activating Token Index: 631

Text #13

Max Range: 3.2423. Min Range: -3.2423

Max Act: 3.0691. Min Act: -0.1700

Data Index: 920234 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 3.2423. Min Range: -3.2423

Max Act: 3.0533. Min Act: -0.1700

Data Index: 1212391 (C4 (Web Text))

Max Activating Token Index: 62

Text #15

Max Range: 3.2423. Min Range: -3.2423

Max Act: 3.0533. Min Act: -0.1700

Data Index: 764140 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 3.2423. Min Range: -3.2423

Max Act: 3.0533. Min Act: -0.1700

Data Index: 710426 (C4 (Web Text))

Max Activating Token Index: 759

Text #17

Max Range: 3.2423. Min Range: -3.2423

Max Act: 3.0691. Min Act: -0.1700

Data Index: 1240728 (C4 (Web Text))

Max Activating Token Index: 274

Text #18

Max Range: 3.2423. Min Range: -3.2423

Max Act: 3.0375. Min Act: -0.1700

Data Index: 1048826 (C4 (Web Text))

Max Activating Token Index: 548

Text #19

Max Range: 3.2423. Min Range: -3.2423

Max Act: 3.0375. Min Act: -0.1700

Data Index: 121863 (C4 (Web Text))

Max Activating Token Index: 426