Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 905 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 4.1133. Min Range: -4.1133

Max Act: 4.1133. Min Act: -0.1700

Data Index: 773203 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 4.1133. Min Range: -4.1133

Max Act: 4.0820. Min Act: -0.1697

Data Index: 1255332 (C4 (Web Text))

Max Activating Token Index: 670

Text #2

Max Range: 4.1133. Min Range: -4.1133

Max Act: 3.9882. Min Act: -0.1700

Data Index: 347421 (C4 (Web Text))

Max Activating Token Index: 572

Text #3

Max Range: 4.1133. Min Range: -4.1133

Max Act: 3.9882. Min Act: -0.1700

Data Index: 371262 (C4 (Web Text))

Max Activating Token Index: 93

Text #4

Max Range: 4.1133. Min Range: -4.1133

Max Act: 3.9570. Min Act: -0.1699

Data Index: 445580 (C4 (Web Text))

Max Activating Token Index: 851

Text #5

Max Range: 4.1133. Min Range: -4.1133

Max Act: 3.9570. Min Act: -0.1700

Data Index: 1191171 (C4 (Web Text))

Max Activating Token Index: 402

Text #6

Max Range: 4.1133. Min Range: -4.1133

Max Act: 3.9257. Min Act: -0.1700

Data Index: 1157264 (C4 (Web Text))

Max Activating Token Index: 1000

Text #7

Max Range: 4.1133. Min Range: -4.1133

Max Act: 3.9257. Min Act: -0.1696

Data Index: 1079605 (C4 (Web Text))

Max Activating Token Index: 831

Text #8

Max Range: 4.1133. Min Range: -4.1133

Max Act: 3.8944. Min Act: -0.1700

Data Index: 97680 (C4 (Web Text))

Max Activating Token Index: 536

Text #9

Max Range: 4.1133. Min Range: -4.1133

Max Act: 3.9257. Min Act: -0.1699

Data Index: 176996 (C4 (Web Text))

Max Activating Token Index: 212

Text #10

Max Range: 4.1133. Min Range: -4.1133

Max Act: 3.8632. Min Act: -0.1700

Data Index: 1047644 (C4 (Web Text))

Max Activating Token Index: 354

Text #11

Max Range: 4.1133. Min Range: -4.1133

Max Act: 3.8944. Min Act: -0.1700

Data Index: 44498 (C4 (Web Text))

Max Activating Token Index: 873

Text #12

Max Range: 4.1133. Min Range: -4.1133

Max Act: 3.8319. Min Act: -0.1699

Data Index: 728622 (C4 (Web Text))

Max Activating Token Index: 653

Text #13

Max Range: 4.1133. Min Range: -4.1133

Max Act: 3.8319. Min Act: -0.1700

Data Index: 257626 (C4 (Web Text))

Max Activating Token Index: 62

Text #14

Max Range: 4.1133. Min Range: -4.1133

Max Act: 3.8319. Min Act: -0.1689

Data Index: 1290672 (C4 (Web Text))

Max Activating Token Index: 567

Text #15

Max Range: 4.1133. Min Range: -4.1133

Max Act: 3.8006. Min Act: -0.1700

Data Index: 1271735 (C4 (Web Text))

Max Activating Token Index: 567

Text #16

Max Range: 4.1133. Min Range: -4.1133

Max Act: 3.8006. Min Act: -0.1700

Data Index: 321356 (C4 (Web Text))

Max Activating Token Index: 369

Text #17

Max Range: 4.1133. Min Range: -4.1133

Max Act: 3.8006. Min Act: -0.1700

Data Index: 283706 (C4 (Web Text))

Max Activating Token Index: 802

Text #18

Max Range: 4.1133. Min Range: -4.1133

Max Act: 3.8006. Min Act: -0.1700

Data Index: 813572 (C4 (Web Text))

Max Activating Token Index: 228

Text #19

Max Range: 4.1133. Min Range: -4.1133

Max Act: 3.7693. Min Act: -0.1700

Data Index: 934146 (C4 (Web Text))

Max Activating Token Index: 686