Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 230 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.6409. Min Range: -5.6409

Max Act: 5.6409. Min Act: -0.1700

Data Index: 976930 (C4 (Web Text))

Max Activating Token Index: 862

Text #1

Max Range: 5.6409. Min Range: -5.6409

Max Act: 5.6097. Min Act: -0.1700

Data Index: 1002971 (C4 (Web Text))

Max Activating Token Index: 557

Text #2

Max Range: 5.6409. Min Range: -5.6409

Max Act: 5.4222. Min Act: -0.1700

Data Index: 1303750 (C4 (Web Text))

Max Activating Token Index: 857

Text #3

Max Range: 5.6409. Min Range: -5.6409

Max Act: 5.3597. Min Act: -0.1700

Data Index: 1508574 (Python Code)

Max Activating Token Index: 75

Text #4

Max Range: 5.6409. Min Range: -5.6409

Max Act: 5.3284. Min Act: -0.1700

Data Index: 1149184 (C4 (Web Text))

Max Activating Token Index: 500

Text #5

Max Range: 5.6409. Min Range: -5.6409

Max Act: 5.3284. Min Act: -0.1700

Data Index: 1139270 (C4 (Web Text))

Max Activating Token Index: 953

Text #6

Max Range: 5.6409. Min Range: -5.6409

Max Act: 5.2972. Min Act: -0.1700

Data Index: 1555878 (Python Code)

Max Activating Token Index: 173

Text #7

Max Range: 5.6409. Min Range: -5.6409

Max Act: 5.3284. Min Act: -0.1700

Data Index: 1393421 (Python Code)

Max Activating Token Index: 857

Text #8

Max Range: 5.6409. Min Range: -5.6409

Max Act: 5.2659. Min Act: -0.1700

Data Index: 195466 (C4 (Web Text))

Max Activating Token Index: 1017

Text #9

Max Range: 5.6409. Min Range: -5.6409

Max Act: 5.2972. Min Act: -0.1700

Data Index: 1650870 (Python Code)

Max Activating Token Index: 795

Text #10

Max Range: 5.6409. Min Range: -5.6409

Max Act: 5.2972. Min Act: -0.1700

Data Index: 217852 (C4 (Web Text))

Max Activating Token Index: 244

Text #11

Max Range: 5.6409. Min Range: -5.6409

Max Act: 5.2972. Min Act: -0.1700

Data Index: 471579 (C4 (Web Text))

Max Activating Token Index: 929

Text #12

Max Range: 5.6409. Min Range: -5.6409

Max Act: 5.2659. Min Act: -0.1700

Data Index: 330466 (C4 (Web Text))

Max Activating Token Index: 535

Text #13

Max Range: 5.6409. Min Range: -5.6409

Max Act: 5.2347. Min Act: -0.1700

Data Index: 1540054 (Python Code)

Max Activating Token Index: 962

Text #14

Max Range: 5.6409. Min Range: -5.6409

Max Act: 5.2347. Min Act: -0.1700

Data Index: 493974 (C4 (Web Text))

Max Activating Token Index: 793

Text #15

Max Range: 5.6409. Min Range: -5.6409

Max Act: 5.2034. Min Act: -0.1700

Data Index: 1090770 (C4 (Web Text))

Max Activating Token Index: 666

Text #16

Max Range: 5.6409. Min Range: -5.6409

Max Act: 5.2347. Min Act: -0.1700

Data Index: 1489415 (Python Code)

Max Activating Token Index: 160

Text #17

Max Range: 5.6409. Min Range: -5.6409

Max Act: 5.1722. Min Act: -0.1700

Data Index: 1547267 (Python Code)

Max Activating Token Index: 665

Text #18

Max Range: 5.6409. Min Range: -5.6409

Max Act: 5.1722. Min Act: -0.1700

Data Index: 1597010 (Python Code)

Max Activating Token Index: 173

Text #19

Max Range: 5.6409. Min Range: -5.6409

Max Act: 5.1409. Min Act: -0.1700

Data Index: 3726 (C4 (Web Text))

Max Activating Token Index: 467