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

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

Neuron 826 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: 5.7369. Min Range: -5.7369

Max Act: 5.6432. Min Act: -0.1700

Data Index: 395971 (C4 (Web Text))

Max Activating Token Index: 654

Text #1

Max Range: 5.7369. Min Range: -5.7369

Max Act: 5.6119. Min Act: -0.1700

Data Index: 661835 (C4 (Web Text))

Max Activating Token Index: 855

Text #2

Max Range: 5.7369. Min Range: -5.7369

Max Act: 5.6432. Min Act: -0.1700

Data Index: 810506 (C4 (Web Text))

Max Activating Token Index: 817

Text #3

Max Range: 5.7369. Min Range: -5.7369

Max Act: 5.7369. Min Act: -0.1700

Data Index: 1268103 (C4 (Web Text))

Max Activating Token Index: 751

Text #4

Max Range: 5.7369. Min Range: -5.7369

Max Act: 5.6744. Min Act: -0.1700

Data Index: 1073677 (C4 (Web Text))

Max Activating Token Index: 501

Text #5

Max Range: 5.7369. Min Range: -5.7369

Max Act: 5.6432. Min Act: -0.1700

Data Index: 191634 (C4 (Web Text))

Max Activating Token Index: 576

Text #6

Max Range: 5.7369. Min Range: -5.7369

Max Act: 5.5807. Min Act: -0.1700

Data Index: 42302 (C4 (Web Text))

Max Activating Token Index: 649

Text #7

Max Range: 5.7369. Min Range: -5.7369

Max Act: 5.6432. Min Act: -0.1700

Data Index: 588839 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 5.7369. Min Range: -5.7369

Max Act: 5.5807. Min Act: -0.1700

Data Index: 256107 (C4 (Web Text))

Max Activating Token Index: 772

Text #9

Max Range: 5.7369. Min Range: -5.7369

Max Act: 5.6432. Min Act: -0.1700

Data Index: 170925 (C4 (Web Text))

Max Activating Token Index: 891

Text #10

Max Range: 5.7369. Min Range: -5.7369

Max Act: 5.5807. Min Act: -0.1700

Data Index: 740143 (C4 (Web Text))

Max Activating Token Index: 430

Text #11

Max Range: 5.7369. Min Range: -5.7369

Max Act: 5.6119. Min Act: -0.1700

Data Index: 459594 (C4 (Web Text))

Max Activating Token Index: 386

Text #12

Max Range: 5.7369. Min Range: -5.7369

Max Act: 5.6119. Min Act: -0.1700

Data Index: 423261 (C4 (Web Text))

Max Activating Token Index: 526

Text #13

Max Range: 5.7369. Min Range: -5.7369

Max Act: 5.5807. Min Act: -0.1700

Data Index: 805299 (C4 (Web Text))

Max Activating Token Index: 443

Text #14

Max Range: 5.7369. Min Range: -5.7369

Max Act: 5.5494. Min Act: -0.1700

Data Index: 1128316 (C4 (Web Text))

Max Activating Token Index: 695

Text #15

Max Range: 5.7369. Min Range: -5.7369

Max Act: 5.5494. Min Act: -0.1700

Data Index: 919779 (C4 (Web Text))

Max Activating Token Index: 645

Text #16

Max Range: 5.7369. Min Range: -5.7369

Max Act: 5.5182. Min Act: -0.1700

Data Index: 191562 (C4 (Web Text))

Max Activating Token Index: 931

Text #17

Max Range: 5.7369. Min Range: -5.7369

Max Act: 5.5494. Min Act: -0.1700

Data Index: 586311 (C4 (Web Text))

Max Activating Token Index: 303

Text #18

Max Range: 5.7369. Min Range: -5.7369

Max Act: 5.4557. Min Act: -0.1700

Data Index: 629115 (C4 (Web Text))

Max Activating Token Index: 230

Text #19

Max Range: 5.7369. Min Range: -5.7369

Max Act: 5.4869. Min Act: -0.1700

Data Index: 1124474 (C4 (Web Text))

Max Activating Token Index: 490