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

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

Neuron 2030 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6932. Min Range: -3.6932

Max Act: 3.6932. Min Act: -0.1700

Data Index: 502843 (C4 (Web Text))

Max Activating Token Index: 378

Text #1

Max Range: 3.6932. Min Range: -3.6932

Max Act: 3.6932. Min Act: -0.1700

Data Index: 673244 (C4 (Web Text))

Max Activating Token Index: 270

Text #2

Max Range: 3.6932. Min Range: -3.6932

Max Act: 3.6619. Min Act: -0.1700

Data Index: 494272 (C4 (Web Text))

Max Activating Token Index: 956

Text #3

Max Range: 3.6932. Min Range: -3.6932

Max Act: 3.6776. Min Act: -0.1700

Data Index: 494435 (C4 (Web Text))

Max Activating Token Index: 904

Text #4

Max Range: 3.6932. Min Range: -3.6932

Max Act: 3.6619. Min Act: -0.1700

Data Index: 1275280 (C4 (Web Text))

Max Activating Token Index: 827

Text #5

Max Range: 3.6932. Min Range: -3.6932

Max Act: 3.6306. Min Act: -0.1700

Data Index: 329618 (C4 (Web Text))

Max Activating Token Index: 630

Text #6

Max Range: 3.6932. Min Range: -3.6932

Max Act: 3.6463. Min Act: -0.1700

Data Index: 881370 (C4 (Web Text))

Max Activating Token Index: 246

Text #7

Max Range: 3.6932. Min Range: -3.6932

Max Act: 3.6619. Min Act: -0.1700

Data Index: 786263 (C4 (Web Text))

Max Activating Token Index: 775

Text #8

Max Range: 3.6932. Min Range: -3.6932

Max Act: 3.6306. Min Act: -0.1700

Data Index: 997074 (C4 (Web Text))

Max Activating Token Index: 362

Text #9

Max Range: 3.6932. Min Range: -3.6932

Max Act: 3.6463. Min Act: -0.1699

Data Index: 561954 (C4 (Web Text))

Max Activating Token Index: 939

Text #10

Max Range: 3.6932. Min Range: -3.6932

Max Act: 3.6306. Min Act: -0.1700

Data Index: 621457 (C4 (Web Text))

Max Activating Token Index: 621

Text #11

Max Range: 3.6932. Min Range: -3.6932

Max Act: 3.6150. Min Act: -0.1700

Data Index: 29292 (C4 (Web Text))

Max Activating Token Index: 824

Text #12

Max Range: 3.6932. Min Range: -3.6932

Max Act: 3.6306. Min Act: -0.1699

Data Index: 819523 (C4 (Web Text))

Max Activating Token Index: 463

Text #13

Max Range: 3.6932. Min Range: -3.6932

Max Act: 3.6150. Min Act: -0.1700

Data Index: 156184 (C4 (Web Text))

Max Activating Token Index: 459

Text #14

Max Range: 3.6932. Min Range: -3.6932

Max Act: 3.6150. Min Act: -0.1700

Data Index: 1066556 (C4 (Web Text))

Max Activating Token Index: 705

Text #15

Max Range: 3.6932. Min Range: -3.6932

Max Act: 3.5993. Min Act: -0.1700

Data Index: 1163238 (C4 (Web Text))

Max Activating Token Index: 424

Text #16

Max Range: 3.6932. Min Range: -3.6932

Max Act: 3.5993. Min Act: -0.1700

Data Index: 967980 (C4 (Web Text))

Max Activating Token Index: 126

Text #17

Max Range: 3.6932. Min Range: -3.6932

Max Act: 3.5837. Min Act: -0.1700

Data Index: 349954 (C4 (Web Text))

Max Activating Token Index: 256

Text #18

Max Range: 3.6932. Min Range: -3.6932

Max Act: 3.6150. Min Act: -0.1700

Data Index: 1066485 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 3.6932. Min Range: -3.6932

Max Act: 3.5993. Min Act: -0.1700

Data Index: 160156 (C4 (Web Text))

Max Activating Token Index: 854