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

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

Neuron 1081 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: 5.7590. Min Range: -5.7590

Max Act: 5.7590. Min Act: -0.1700

Data Index: 791628 (C4 (Web Text))

Max Activating Token Index: 169

Text #1

Max Range: 5.7590. Min Range: -5.7590

Max Act: 5.7590. Min Act: -0.1700

Data Index: 1262911 (C4 (Web Text))

Max Activating Token Index: 774

Text #2

Max Range: 5.7590. Min Range: -5.7590

Max Act: 5.6965. Min Act: -0.1700

Data Index: 958438 (C4 (Web Text))

Max Activating Token Index: 740

Text #3

Max Range: 5.7590. Min Range: -5.7590

Max Act: 5.6652. Min Act: -0.1700

Data Index: 185129 (C4 (Web Text))

Max Activating Token Index: 613

Text #4

Max Range: 5.7590. Min Range: -5.7590

Max Act: 5.5715. Min Act: -0.1700

Data Index: 1074075 (C4 (Web Text))

Max Activating Token Index: 223

Text #5

Max Range: 5.7590. Min Range: -5.7590

Max Act: 5.6027. Min Act: -0.1700

Data Index: 621656 (C4 (Web Text))

Max Activating Token Index: 148

Text #6

Max Range: 5.7590. Min Range: -5.7590

Max Act: 5.6340. Min Act: -0.1700

Data Index: 780846 (C4 (Web Text))

Max Activating Token Index: 19

Text #7

Max Range: 5.7590. Min Range: -5.7590

Max Act: 5.6340. Min Act: -0.1700

Data Index: 415251 (C4 (Web Text))

Max Activating Token Index: 866

Text #8

Max Range: 5.7590. Min Range: -5.7590

Max Act: 5.5402. Min Act: -0.1700

Data Index: 1313931 (C4 (Web Text))

Max Activating Token Index: 249

Text #9

Max Range: 5.7590. Min Range: -5.7590

Max Act: 5.4465. Min Act: -0.1700

Data Index: 1283583 (C4 (Web Text))

Max Activating Token Index: 699

Text #10

Max Range: 5.7590. Min Range: -5.7590

Max Act: 5.4152. Min Act: -0.1700

Data Index: 256110 (C4 (Web Text))

Max Activating Token Index: 515

Text #11

Max Range: 5.7590. Min Range: -5.7590

Max Act: 5.4152. Min Act: -0.1700

Data Index: 993516 (C4 (Web Text))

Max Activating Token Index: 957

Text #12

Max Range: 5.7590. Min Range: -5.7590

Max Act: 5.4152. Min Act: -0.1700

Data Index: 1342554 (C4 (Web Text))

Max Activating Token Index: 77

Text #13

Max Range: 5.7590. Min Range: -5.7590

Max Act: 5.4777. Min Act: -0.1700

Data Index: 1268641 (C4 (Web Text))

Max Activating Token Index: 542

Text #14

Max Range: 5.7590. Min Range: -5.7590

Max Act: 5.3840. Min Act: -0.1700

Data Index: 1106006 (C4 (Web Text))

Max Activating Token Index: 502

Text #15

Max Range: 5.7590. Min Range: -5.7590

Max Act: 5.3840. Min Act: -0.1700

Data Index: 1046071 (C4 (Web Text))

Max Activating Token Index: 828

Text #16

Max Range: 5.7590. Min Range: -5.7590

Max Act: 5.3840. Min Act: -0.1700

Data Index: 145491 (C4 (Web Text))

Max Activating Token Index: 27

Text #17

Max Range: 5.7590. Min Range: -5.7590

Max Act: 5.3840. Min Act: -0.1700

Data Index: 858804 (C4 (Web Text))

Max Activating Token Index: 865

Text #18

Max Range: 5.7590. Min Range: -5.7590

Max Act: 5.3840. Min Act: -0.1700

Data Index: 274949 (C4 (Web Text))

Max Activating Token Index: 1006

Text #19

Max Range: 5.7590. Min Range: -5.7590

Max Act: 5.3527. Min Act: -0.1700

Data Index: 57236 (C4 (Web Text))

Max Activating Token Index: 767