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

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

Neuron 1800 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3386. Min Range: -3.3386

Max Act: 3.3386. Min Act: -0.1700

Data Index: 304860 (C4 (Web Text))

Max Activating Token Index: 126

Text #1

Max Range: 3.3386. Min Range: -3.3386

Max Act: 3.3072. Min Act: -0.1700

Data Index: 189350 (C4 (Web Text))

Max Activating Token Index: 271

Text #2

Max Range: 3.3386. Min Range: -3.3386

Max Act: 3.3072. Min Act: -0.1700

Data Index: 1079145 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 3.3386. Min Range: -3.3386

Max Act: 3.2758. Min Act: -0.1700

Data Index: 34254 (C4 (Web Text))

Max Activating Token Index: 650

Text #4

Max Range: 3.3386. Min Range: -3.3386

Max Act: 3.2601. Min Act: -0.1700

Data Index: 996138 (C4 (Web Text))

Max Activating Token Index: 63

Text #5

Max Range: 3.3386. Min Range: -3.3386

Max Act: 3.2601. Min Act: -0.1700

Data Index: 272552 (C4 (Web Text))

Max Activating Token Index: 104

Text #6

Max Range: 3.3386. Min Range: -3.3386

Max Act: 3.2601. Min Act: -0.1700

Data Index: 371928 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 3.3386. Min Range: -3.3386

Max Act: 3.2287. Min Act: -0.1700

Data Index: 1007549 (C4 (Web Text))

Max Activating Token Index: 280

Text #8

Max Range: 3.3386. Min Range: -3.3386

Max Act: 3.2287. Min Act: -0.1700

Data Index: 1097137 (C4 (Web Text))

Max Activating Token Index: 440

Text #9

Max Range: 3.3386. Min Range: -3.3386

Max Act: 3.2287. Min Act: -0.1700

Data Index: 144190 (C4 (Web Text))

Max Activating Token Index: 392

Text #10

Max Range: 3.3386. Min Range: -3.3386

Max Act: 3.2287. Min Act: -0.1700

Data Index: 105272 (C4 (Web Text))

Max Activating Token Index: 989

Text #11

Max Range: 3.3386. Min Range: -3.3386

Max Act: 3.1972. Min Act: -0.1700

Data Index: 1258357 (C4 (Web Text))

Max Activating Token Index: 100

Text #12

Max Range: 3.3386. Min Range: -3.3386

Max Act: 3.1972. Min Act: -0.1700

Data Index: 1073468 (C4 (Web Text))

Max Activating Token Index: 606

Text #13

Max Range: 3.3386. Min Range: -3.3386

Max Act: 3.1815. Min Act: -0.1700

Data Index: 1274998 (C4 (Web Text))

Max Activating Token Index: 373

Text #14

Max Range: 3.3386. Min Range: -3.3386

Max Act: 3.1500. Min Act: -0.1700

Data Index: 969724 (C4 (Web Text))

Max Activating Token Index: 324

Text #15

Max Range: 3.3386. Min Range: -3.3386

Max Act: 3.1500. Min Act: -0.1700

Data Index: 1267852 (C4 (Web Text))

Max Activating Token Index: 479

Text #16

Max Range: 3.3386. Min Range: -3.3386

Max Act: 3.1500. Min Act: -0.1700

Data Index: 1355008 (C4 (Web Text))

Max Activating Token Index: 554

Text #17

Max Range: 3.3386. Min Range: -3.3386

Max Act: 3.1185. Min Act: -0.1700

Data Index: 460072 (C4 (Web Text))

Max Activating Token Index: 630

Text #18

Max Range: 3.3386. Min Range: -3.3386

Max Act: 3.1342. Min Act: -0.1700

Data Index: 1332254 (C4 (Web Text))

Max Activating Token Index: 542

Text #19

Max Range: 3.3386. Min Range: -3.3386

Max Act: 3.1027. Min Act: -0.1700

Data Index: 1014768 (C4 (Web Text))

Max Activating Token Index: 549