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

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

Neuron 1232 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: 5.7151. Min Range: -5.7151

Max Act: 5.7151. Min Act: -0.1699

Data Index: 1100649 (C4 (Web Text))

Max Activating Token Index: 786

Text #1

Max Range: 5.7151. Min Range: -5.7151

Max Act: 5.1291. Min Act: -0.1699

Data Index: 386446 (C4 (Web Text))

Max Activating Token Index: 783

Text #2

Max Range: 5.7151. Min Range: -5.7151

Max Act: 5.1604. Min Act: -0.1699

Data Index: 1524290 (Python Code)

Max Activating Token Index: 25

Text #3

Max Range: 5.7151. Min Range: -5.7151

Max Act: 5.0901. Min Act: -0.1699

Data Index: 1641486 (Python Code)

Max Activating Token Index: 81

Text #4

Max Range: 5.7151. Min Range: -5.7151

Max Act: 5.0744. Min Act: -0.1699

Data Index: 1076341 (C4 (Web Text))

Max Activating Token Index: 433

Text #5

Max Range: 5.7151. Min Range: -5.7151

Max Act: 5.0354. Min Act: -0.1699

Data Index: 1597140 (Python Code)

Max Activating Token Index: 634

Text #6

Max Range: 5.7151. Min Range: -5.7151

Max Act: 5.0744. Min Act: -0.1699

Data Index: 805939 (C4 (Web Text))

Max Activating Token Index: 62

Text #7

Max Range: 5.7151. Min Range: -5.7151

Max Act: 5.0979. Min Act: -0.1699

Data Index: 202754 (C4 (Web Text))

Max Activating Token Index: 358

Text #8

Max Range: 5.7151. Min Range: -5.7151

Max Act: 5.0354. Min Act: -0.1699

Data Index: 1382278 (Python Code)

Max Activating Token Index: 108

Text #9

Max Range: 5.7151. Min Range: -5.7151

Max Act: 5.0041. Min Act: -0.1699

Data Index: 528354 (C4 (Web Text))

Max Activating Token Index: 630

Text #10

Max Range: 5.7151. Min Range: -5.7151

Max Act: 4.8869. Min Act: -0.1699

Data Index: 595179 (C4 (Web Text))

Max Activating Token Index: 915

Text #11

Max Range: 5.7151. Min Range: -5.7151

Max Act: 4.9729. Min Act: -0.1699

Data Index: 939197 (C4 (Web Text))

Max Activating Token Index: 341

Text #12

Max Range: 5.7151. Min Range: -5.7151

Max Act: 4.9963. Min Act: -0.1699

Data Index: 192285 (C4 (Web Text))

Max Activating Token Index: 930

Text #13

Max Range: 5.7151. Min Range: -5.7151

Max Act: 4.9885. Min Act: -0.1699

Data Index: 486205 (C4 (Web Text))

Max Activating Token Index: 553

Text #14

Max Range: 5.7151. Min Range: -5.7151

Max Act: 4.9885. Min Act: -0.1699

Data Index: 1083095 (C4 (Web Text))

Max Activating Token Index: 133

Text #15

Max Range: 5.7151. Min Range: -5.7151

Max Act: 4.9885. Min Act: -0.1699

Data Index: 730123 (C4 (Web Text))

Max Activating Token Index: 94

Text #16

Max Range: 5.7151. Min Range: -5.7151

Max Act: 4.9807. Min Act: -0.1699

Data Index: 792047 (C4 (Web Text))

Max Activating Token Index: 948

Text #17

Max Range: 5.7151. Min Range: -5.7151

Max Act: 4.9807. Min Act: -0.1699

Data Index: 1288103 (C4 (Web Text))

Max Activating Token Index: 352

Text #18

Max Range: 5.7151. Min Range: -5.7151

Max Act: 4.9494. Min Act: -0.1699

Data Index: 1008093 (C4 (Web Text))

Max Activating Token Index: 466

Text #19

Max Range: 5.7151. Min Range: -5.7151

Max Act: 4.9807. Min Act: -0.1699

Data Index: 1076500 (C4 (Web Text))

Max Activating Token Index: 741