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

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

Neuron 188 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: 5.1327. Min Range: -5.1327

Max Act: 5.1327. Min Act: -0.1700

Data Index: 213167 (C4 (Web Text))

Max Activating Token Index: 786

Text #1

Max Range: 5.1327. Min Range: -5.1327

Max Act: 5.0389. Min Act: -0.1700

Data Index: 689092 (C4 (Web Text))

Max Activating Token Index: 439

Text #2

Max Range: 5.1327. Min Range: -5.1327

Max Act: 5.0077. Min Act: -0.1700

Data Index: 645253 (C4 (Web Text))

Max Activating Token Index: 467

Text #3

Max Range: 5.1327. Min Range: -5.1327

Max Act: 4.9452. Min Act: -0.1700

Data Index: 1131317 (C4 (Web Text))

Max Activating Token Index: 594

Text #4

Max Range: 5.1327. Min Range: -5.1327

Max Act: 4.9452. Min Act: -0.1700

Data Index: 310862 (C4 (Web Text))

Max Activating Token Index: 722

Text #5

Max Range: 5.1327. Min Range: -5.1327

Max Act: 4.8514. Min Act: -0.1700

Data Index: 517384 (C4 (Web Text))

Max Activating Token Index: 898

Text #6

Max Range: 5.1327. Min Range: -5.1327

Max Act: 4.7577. Min Act: -0.1700

Data Index: 132963 (C4 (Web Text))

Max Activating Token Index: 802

Text #7

Max Range: 5.1327. Min Range: -5.1327

Max Act: 4.8827. Min Act: -0.1700

Data Index: 837652 (C4 (Web Text))

Max Activating Token Index: 991

Text #8

Max Range: 5.1327. Min Range: -5.1327

Max Act: 4.8514. Min Act: -0.1700

Data Index: 23663 (C4 (Web Text))

Max Activating Token Index: 79

Text #9

Max Range: 5.1327. Min Range: -5.1327

Max Act: 4.8202. Min Act: -0.1700

Data Index: 436147 (C4 (Web Text))

Max Activating Token Index: 949

Text #10

Max Range: 5.1327. Min Range: -5.1327

Max Act: 4.7889. Min Act: -0.1700

Data Index: 71704 (C4 (Web Text))

Max Activating Token Index: 748

Text #11

Max Range: 5.1327. Min Range: -5.1327

Max Act: 4.7889. Min Act: -0.1700

Data Index: 132268 (C4 (Web Text))

Max Activating Token Index: 873

Text #12

Max Range: 5.1327. Min Range: -5.1327

Max Act: 4.8202. Min Act: -0.1700

Data Index: 774390 (C4 (Web Text))

Max Activating Token Index: 429

Text #13

Max Range: 5.1327. Min Range: -5.1327

Max Act: 4.7889. Min Act: -0.1700

Data Index: 20379 (C4 (Web Text))

Max Activating Token Index: 788

Text #14

Max Range: 5.1327. Min Range: -5.1327

Max Act: 4.7889. Min Act: -0.1700

Data Index: 210103 (C4 (Web Text))

Max Activating Token Index: 669

Text #15

Max Range: 5.1327. Min Range: -5.1327

Max Act: 4.7577. Min Act: -0.1700

Data Index: 110380 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 5.1327. Min Range: -5.1327

Max Act: 4.7889. Min Act: -0.1700

Data Index: 933121 (C4 (Web Text))

Max Activating Token Index: 871

Text #17

Max Range: 5.1327. Min Range: -5.1327

Max Act: 4.6952. Min Act: -0.1700

Data Index: 228796 (C4 (Web Text))

Max Activating Token Index: 544

Text #18

Max Range: 5.1327. Min Range: -5.1327

Max Act: 4.6639. Min Act: -0.1700

Data Index: 892553 (C4 (Web Text))

Max Activating Token Index: 231

Text #19

Max Range: 5.1327. Min Range: -5.1327

Max Act: 4.7264. Min Act: -0.1700

Data Index: 1021273 (C4 (Web Text))

Max Activating Token Index: 124