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

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

Neuron 1452 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: 5.2230. Min Range: -5.2230

Max Act: 5.2230. Min Act: -0.1700

Data Index: 72222 (C4 (Web Text))

Max Activating Token Index: 917

Text #1

Max Range: 5.2230. Min Range: -5.2230

Max Act: 5.1293. Min Act: -0.1700

Data Index: 296599 (C4 (Web Text))

Max Activating Token Index: 716

Text #2

Max Range: 5.2230. Min Range: -5.2230

Max Act: 5.1293. Min Act: -0.1700

Data Index: 684401 (C4 (Web Text))

Max Activating Token Index: 438

Text #3

Max Range: 5.2230. Min Range: -5.2230

Max Act: 5.0355. Min Act: -0.1700

Data Index: 738591 (C4 (Web Text))

Max Activating Token Index: 878

Text #4

Max Range: 5.2230. Min Range: -5.2230

Max Act: 4.9730. Min Act: -0.1700

Data Index: 647920 (C4 (Web Text))

Max Activating Token Index: 233

Text #5

Max Range: 5.2230. Min Range: -5.2230

Max Act: 5.0043. Min Act: -0.1700

Data Index: 1284979 (C4 (Web Text))

Max Activating Token Index: 683

Text #6

Max Range: 5.2230. Min Range: -5.2230

Max Act: 4.8793. Min Act: -0.1700

Data Index: 1099283 (C4 (Web Text))

Max Activating Token Index: 469

Text #7

Max Range: 5.2230. Min Range: -5.2230

Max Act: 5.0355. Min Act: -0.1700

Data Index: 872144 (C4 (Web Text))

Max Activating Token Index: 803

Text #8

Max Range: 5.2230. Min Range: -5.2230

Max Act: 4.9418. Min Act: -0.1700

Data Index: 954605 (C4 (Web Text))

Max Activating Token Index: 971

Text #9

Max Range: 5.2230. Min Range: -5.2230

Max Act: 4.9418. Min Act: -0.1700

Data Index: 707034 (C4 (Web Text))

Max Activating Token Index: 662

Text #10

Max Range: 5.2230. Min Range: -5.2230

Max Act: 4.8793. Min Act: -0.1700

Data Index: 965724 (C4 (Web Text))

Max Activating Token Index: 599

Text #11

Max Range: 5.2230. Min Range: -5.2230

Max Act: 4.9105. Min Act: -0.1700

Data Index: 1103170 (C4 (Web Text))

Max Activating Token Index: 522

Text #12

Max Range: 5.2230. Min Range: -5.2230

Max Act: 4.8793. Min Act: -0.1700

Data Index: 656711 (C4 (Web Text))

Max Activating Token Index: 440

Text #13

Max Range: 5.2230. Min Range: -5.2230

Max Act: 4.8480. Min Act: -0.1700

Data Index: 824762 (C4 (Web Text))

Max Activating Token Index: 239

Text #14

Max Range: 5.2230. Min Range: -5.2230

Max Act: 4.7855. Min Act: -0.1700

Data Index: 242049 (C4 (Web Text))

Max Activating Token Index: 322

Text #15

Max Range: 5.2230. Min Range: -5.2230

Max Act: 4.9105. Min Act: -0.1700

Data Index: 1188178 (C4 (Web Text))

Max Activating Token Index: 386

Text #16

Max Range: 5.2230. Min Range: -5.2230

Max Act: 4.8480. Min Act: -0.1700

Data Index: 7471 (C4 (Web Text))

Max Activating Token Index: 842

Text #17

Max Range: 5.2230. Min Range: -5.2230

Max Act: 4.8168. Min Act: -0.1700

Data Index: 1356063 (C4 (Web Text))

Max Activating Token Index: 922

Text #18

Max Range: 5.2230. Min Range: -5.2230

Max Act: 4.7543. Min Act: -0.1700

Data Index: 147380 (C4 (Web Text))

Max Activating Token Index: 228

Text #19

Max Range: 5.2230. Min Range: -5.2230

Max Act: 4.6918. Min Act: -0.1700

Data Index: 113031 (C4 (Web Text))

Max Activating Token Index: 293