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

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

Neuron 878 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: 5.1616. Min Range: -5.1616

Max Act: 5.1616. Min Act: -0.1700

Data Index: 1151431 (C4 (Web Text))

Max Activating Token Index: 300

Text #1

Max Range: 5.1616. Min Range: -5.1616

Max Act: 5.1147. Min Act: -0.1700

Data Index: 297471 (C4 (Web Text))

Max Activating Token Index: 773

Text #2

Max Range: 5.1616. Min Range: -5.1616

Max Act: 4.7241. Min Act: -0.1700

Data Index: 239287 (C4 (Web Text))

Max Activating Token Index: 384

Text #3

Max Range: 5.1616. Min Range: -5.1616

Max Act: 4.7241. Min Act: -0.1700

Data Index: 944682 (C4 (Web Text))

Max Activating Token Index: 1019

Text #4

Max Range: 5.1616. Min Range: -5.1616

Max Act: 4.6460. Min Act: -0.1700

Data Index: 755382 (C4 (Web Text))

Max Activating Token Index: 676

Text #5

Max Range: 5.1616. Min Range: -5.1616

Max Act: 4.6772. Min Act: -0.1700

Data Index: 962912 (C4 (Web Text))

Max Activating Token Index: 456

Text #6

Max Range: 5.1616. Min Range: -5.1616

Max Act: 4.6304. Min Act: -0.1700

Data Index: 1199421 (C4 (Web Text))

Max Activating Token Index: 570

Text #7

Max Range: 5.1616. Min Range: -5.1616

Max Act: 4.6304. Min Act: -0.1700

Data Index: 1257650 (C4 (Web Text))

Max Activating Token Index: 966

Text #8

Max Range: 5.1616. Min Range: -5.1616

Max Act: 4.6772. Min Act: -0.1700

Data Index: 1095649 (C4 (Web Text))

Max Activating Token Index: 359

Text #9

Max Range: 5.1616. Min Range: -5.1616

Max Act: 4.5835. Min Act: -0.1700

Data Index: 881846 (C4 (Web Text))

Max Activating Token Index: 483

Text #10

Max Range: 5.1616. Min Range: -5.1616

Max Act: 4.6147. Min Act: -0.1700

Data Index: 41955 (C4 (Web Text))

Max Activating Token Index: 1011

Text #11

Max Range: 5.1616. Min Range: -5.1616

Max Act: 4.5991. Min Act: -0.1700

Data Index: 737600 (C4 (Web Text))

Max Activating Token Index: 248

Text #12

Max Range: 5.1616. Min Range: -5.1616

Max Act: 4.5522. Min Act: -0.1700

Data Index: 332683 (C4 (Web Text))

Max Activating Token Index: 149

Text #13

Max Range: 5.1616. Min Range: -5.1616

Max Act: 4.5054. Min Act: -0.1700

Data Index: 552615 (C4 (Web Text))

Max Activating Token Index: 584

Text #14

Max Range: 5.1616. Min Range: -5.1616

Max Act: 4.5366. Min Act: -0.1700

Data Index: 944345 (C4 (Web Text))

Max Activating Token Index: 433

Text #15

Max Range: 5.1616. Min Range: -5.1616

Max Act: 4.5054. Min Act: -0.1700

Data Index: 227985 (C4 (Web Text))

Max Activating Token Index: 510

Text #16

Max Range: 5.1616. Min Range: -5.1616

Max Act: 4.4741. Min Act: -0.1700

Data Index: 1101910 (C4 (Web Text))

Max Activating Token Index: 699

Text #17

Max Range: 5.1616. Min Range: -5.1616

Max Act: 4.4897. Min Act: -0.1700

Data Index: 1227868 (C4 (Web Text))

Max Activating Token Index: 857

Text #18

Max Range: 5.1616. Min Range: -5.1616

Max Act: 4.4741. Min Act: -0.1700

Data Index: 777631 (C4 (Web Text))

Max Activating Token Index: 407

Text #19

Max Range: 5.1616. Min Range: -5.1616

Max Act: 4.5366. Min Act: -0.1700

Data Index: 1269979 (C4 (Web Text))

Max Activating Token Index: 440