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

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

Neuron 790 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: 5.2866. Min Range: -5.2866

Max Act: 5.2866. Min Act: -0.1700

Data Index: 312189 (C4 (Web Text))

Max Activating Token Index: 519

Text #1

Max Range: 5.2866. Min Range: -5.2866

Max Act: 5.2241. Min Act: -0.1700

Data Index: 775770 (C4 (Web Text))

Max Activating Token Index: 355

Text #2

Max Range: 5.2866. Min Range: -5.2866

Max Act: 5.1616. Min Act: -0.1700

Data Index: 1177434 (C4 (Web Text))

Max Activating Token Index: 614

Text #3

Max Range: 5.2866. Min Range: -5.2866

Max Act: 5.0991. Min Act: -0.1700

Data Index: 959743 (C4 (Web Text))

Max Activating Token Index: 141

Text #4

Max Range: 5.2866. Min Range: -5.2866

Max Act: 5.0991. Min Act: -0.1700

Data Index: 1100071 (C4 (Web Text))

Max Activating Token Index: 997

Text #5

Max Range: 5.2866. Min Range: -5.2866

Max Act: 5.0366. Min Act: -0.1700

Data Index: 1308820 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 5.2866. Min Range: -5.2866

Max Act: 4.9741. Min Act: -0.1700

Data Index: 1212794 (C4 (Web Text))

Max Activating Token Index: 251

Text #7

Max Range: 5.2866. Min Range: -5.2866

Max Act: 5.0366. Min Act: -0.1700

Data Index: 332070 (C4 (Web Text))

Max Activating Token Index: 65

Text #8

Max Range: 5.2866. Min Range: -5.2866

Max Act: 5.0053. Min Act: -0.1700

Data Index: 38189 (C4 (Web Text))

Max Activating Token Index: 889

Text #9

Max Range: 5.2866. Min Range: -5.2866

Max Act: 4.9741. Min Act: -0.1700

Data Index: 745731 (C4 (Web Text))

Max Activating Token Index: 740

Text #10

Max Range: 5.2866. Min Range: -5.2866

Max Act: 4.9741. Min Act: -0.1700

Data Index: 968327 (C4 (Web Text))

Max Activating Token Index: 791

Text #11

Max Range: 5.2866. Min Range: -5.2866

Max Act: 4.9741. Min Act: -0.1700

Data Index: 1032238 (C4 (Web Text))

Max Activating Token Index: 456

Text #12

Max Range: 5.2866. Min Range: -5.2866

Max Act: 4.9428. Min Act: -0.1700

Data Index: 1082029 (C4 (Web Text))

Max Activating Token Index: 102

Text #13

Max Range: 5.2866. Min Range: -5.2866

Max Act: 4.8491. Min Act: -0.1700

Data Index: 797520 (C4 (Web Text))

Max Activating Token Index: 579

Text #14

Max Range: 5.2866. Min Range: -5.2866

Max Act: 4.8491. Min Act: -0.1699

Data Index: 508103 (C4 (Web Text))

Max Activating Token Index: 293

Text #15

Max Range: 5.2866. Min Range: -5.2866

Max Act: 4.8803. Min Act: -0.1700

Data Index: 147286 (C4 (Web Text))

Max Activating Token Index: 526

Text #16

Max Range: 5.2866. Min Range: -5.2866

Max Act: 4.7866. Min Act: -0.1700

Data Index: 875343 (C4 (Web Text))

Max Activating Token Index: 900

Text #17

Max Range: 5.2866. Min Range: -5.2866

Max Act: 4.7866. Min Act: -0.1700

Data Index: 43251 (C4 (Web Text))

Max Activating Token Index: 410

Text #18

Max Range: 5.2866. Min Range: -5.2866

Max Act: 4.8491. Min Act: -0.1700

Data Index: 964255 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 5.2866. Min Range: -5.2866

Max Act: 4.7553. Min Act: -0.1700

Data Index: 1055600 (C4 (Web Text))

Max Activating Token Index: 988