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

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

Neuron 176 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3181. Min Range: -3.3181

Max Act: 3.3181. Min Act: -0.1700

Data Index: 620335 (C4 (Web Text))

Max Activating Token Index: 492

Text #1

Max Range: 3.3181. Min Range: -3.3181

Max Act: 3.2553. Min Act: -0.1700

Data Index: 438888 (C4 (Web Text))

Max Activating Token Index: 674

Text #2

Max Range: 3.3181. Min Range: -3.3181

Max Act: 3.2081. Min Act: -0.1700

Data Index: 771345 (C4 (Web Text))

Max Activating Token Index: 489

Text #3

Max Range: 3.3181. Min Range: -3.3181

Max Act: 3.1609. Min Act: -0.1700

Data Index: 1214331 (C4 (Web Text))

Max Activating Token Index: 247

Text #4

Max Range: 3.3181. Min Range: -3.3181

Max Act: 3.1451. Min Act: -0.1700

Data Index: 580810 (C4 (Web Text))

Max Activating Token Index: 768

Text #5

Max Range: 3.3181. Min Range: -3.3181

Max Act: 3.1294. Min Act: -0.1700

Data Index: 824364 (C4 (Web Text))

Max Activating Token Index: 451

Text #6

Max Range: 3.3181. Min Range: -3.3181

Max Act: 3.1136. Min Act: -0.1700

Data Index: 713404 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 3.3181. Min Range: -3.3181

Max Act: 3.0979. Min Act: -0.1700

Data Index: 1335565 (C4 (Web Text))

Max Activating Token Index: 840

Text #8

Max Range: 3.3181. Min Range: -3.3181

Max Act: 3.0663. Min Act: -0.1700

Data Index: 1413643 (Python Code)

Max Activating Token Index: 320

Text #9

Max Range: 3.3181. Min Range: -3.3181

Max Act: 3.0505. Min Act: -0.1700

Data Index: 1025410 (C4 (Web Text))

Max Activating Token Index: 39

Text #10

Max Range: 3.3181. Min Range: -3.3181

Max Act: 3.0979. Min Act: -0.1700

Data Index: 165012 (C4 (Web Text))

Max Activating Token Index: 399

Text #11

Max Range: 3.3181. Min Range: -3.3181

Max Act: 3.0663. Min Act: -0.1700

Data Index: 818356 (C4 (Web Text))

Max Activating Token Index: 108

Text #12

Max Range: 3.3181. Min Range: -3.3181

Max Act: 3.0663. Min Act: -0.1700

Data Index: 1167747 (C4 (Web Text))

Max Activating Token Index: 490

Text #13

Max Range: 3.3181. Min Range: -3.3181

Max Act: 3.0663. Min Act: -0.1700

Data Index: 1295929 (C4 (Web Text))

Max Activating Token Index: 576

Text #14

Max Range: 3.3181. Min Range: -3.3181

Max Act: 3.0505. Min Act: -0.1700

Data Index: 1550190 (Python Code)

Max Activating Token Index: 23

Text #15

Max Range: 3.3181. Min Range: -3.3181

Max Act: 3.0189. Min Act: -0.1700

Data Index: 1116687 (C4 (Web Text))

Max Activating Token Index: 643

Text #16

Max Range: 3.3181. Min Range: -3.3181

Max Act: 3.0031. Min Act: -0.1700

Data Index: 882453 (C4 (Web Text))

Max Activating Token Index: 366

Text #17

Max Range: 3.3181. Min Range: -3.3181

Max Act: 3.0189. Min Act: -0.1700

Data Index: 1279869 (C4 (Web Text))

Max Activating Token Index: 908

Text #18

Max Range: 3.3181. Min Range: -3.3181

Max Act: 3.0347. Min Act: -0.1700

Data Index: 219682 (C4 (Web Text))

Max Activating Token Index: 252

Text #19

Max Range: 3.3181. Min Range: -3.3181

Max Act: 3.0189. Min Act: -0.1700

Data Index: 323933 (C4 (Web Text))

Max Activating Token Index: 618