Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1343 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.9205. Min Range: -3.9205

Max Act: 3.9205. Min Act: -0.1700

Data Index: 522320 (C4 (Web Text))

Max Activating Token Index: 953

Text #1

Max Range: 3.9205. Min Range: -3.9205

Max Act: 3.6702. Min Act: -0.1700

Data Index: 623379 (C4 (Web Text))

Max Activating Token Index: 1015

Text #2

Max Range: 3.9205. Min Range: -3.9205

Max Act: 3.6076. Min Act: -0.1700

Data Index: 1164467 (C4 (Web Text))

Max Activating Token Index: 990

Text #3

Max Range: 3.9205. Min Range: -3.9205

Max Act: 3.5763. Min Act: -0.1700

Data Index: 1080936 (C4 (Web Text))

Max Activating Token Index: 395

Text #4

Max Range: 3.9205. Min Range: -3.9205

Max Act: 3.5450. Min Act: -0.1699

Data Index: 1410466 (Python Code)

Max Activating Token Index: 997

Text #5

Max Range: 3.9205. Min Range: -3.9205

Max Act: 3.5450. Min Act: -0.1700

Data Index: 1095508 (C4 (Web Text))

Max Activating Token Index: 352

Text #6

Max Range: 3.9205. Min Range: -3.9205

Max Act: 3.4509. Min Act: -0.1700

Data Index: 234216 (C4 (Web Text))

Max Activating Token Index: 1010

Text #7

Max Range: 3.9205. Min Range: -3.9205

Max Act: 3.4823. Min Act: -0.1700

Data Index: 546811 (C4 (Web Text))

Max Activating Token Index: 782

Text #8

Max Range: 3.9205. Min Range: -3.9205

Max Act: 3.4509. Min Act: -0.1700

Data Index: 1412408 (Python Code)

Max Activating Token Index: 788

Text #9

Max Range: 3.9205. Min Range: -3.9205

Max Act: 3.4509. Min Act: -0.1700

Data Index: 1442126 (Python Code)

Max Activating Token Index: 533

Text #10

Max Range: 3.9205. Min Range: -3.9205

Max Act: 3.4509. Min Act: -0.1700

Data Index: 1614410 (Python Code)

Max Activating Token Index: 812

Text #11

Max Range: 3.9205. Min Range: -3.9205

Max Act: 3.4509. Min Act: -0.1700

Data Index: 261064 (C4 (Web Text))

Max Activating Token Index: 550

Text #12

Max Range: 3.9205. Min Range: -3.9205

Max Act: 3.4509. Min Act: -0.1700

Data Index: 1005986 (C4 (Web Text))

Max Activating Token Index: 483

Text #13

Max Range: 3.9205. Min Range: -3.9205

Max Act: 3.4509. Min Act: -0.1700

Data Index: 858197 (C4 (Web Text))

Max Activating Token Index: 921

Text #14

Max Range: 3.9205. Min Range: -3.9205

Max Act: 3.4509. Min Act: -0.1700

Data Index: 119635 (C4 (Web Text))

Max Activating Token Index: 950

Text #15

Max Range: 3.9205. Min Range: -3.9205

Max Act: 3.4196. Min Act: -0.1700

Data Index: 976799 (C4 (Web Text))

Max Activating Token Index: 417

Text #16

Max Range: 3.9205. Min Range: -3.9205

Max Act: 3.4509. Min Act: -0.1700

Data Index: 444382 (C4 (Web Text))

Max Activating Token Index: 979

Text #17

Max Range: 3.9205. Min Range: -3.9205

Max Act: 3.4196. Min Act: -0.1700

Data Index: 1293320 (C4 (Web Text))

Max Activating Token Index: 917

Text #18

Max Range: 3.9205. Min Range: -3.9205

Max Act: 3.4196. Min Act: -0.1700

Data Index: 544952 (C4 (Web Text))

Max Activating Token Index: 440

Text #19

Max Range: 3.9205. Min Range: -3.9205

Max Act: 3.4196. Min Act: -0.1700

Data Index: 150478 (C4 (Web Text))

Max Activating Token Index: 960