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

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

Neuron 1465 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: 3.7989. Min Range: -3.7989

Max Act: 3.7989. Min Act: -0.1700

Data Index: 141027 (C4 (Web Text))

Max Activating Token Index: 140

Text #1

Max Range: 3.7989. Min Range: -3.7989

Max Act: 3.7677. Min Act: -0.1700

Data Index: 310426 (C4 (Web Text))

Max Activating Token Index: 915

Text #2

Max Range: 3.7989. Min Range: -3.7989

Max Act: 3.7677. Min Act: -0.1700

Data Index: 1266247 (C4 (Web Text))

Max Activating Token Index: 199

Text #3

Max Range: 3.7989. Min Range: -3.7989

Max Act: 3.7989. Min Act: -0.1700

Data Index: 1096790 (C4 (Web Text))

Max Activating Token Index: 874

Text #4

Max Range: 3.7989. Min Range: -3.7989

Max Act: 3.7677. Min Act: -0.1700

Data Index: 146709 (C4 (Web Text))

Max Activating Token Index: 336

Text #5

Max Range: 3.7989. Min Range: -3.7989

Max Act: 3.7677. Min Act: -0.1700

Data Index: 538263 (C4 (Web Text))

Max Activating Token Index: 328

Text #6

Max Range: 3.7989. Min Range: -3.7989

Max Act: 3.7364. Min Act: -0.1700

Data Index: 394652 (C4 (Web Text))

Max Activating Token Index: 317

Text #7

Max Range: 3.7989. Min Range: -3.7989

Max Act: 3.7364. Min Act: -0.1700

Data Index: 987586 (C4 (Web Text))

Max Activating Token Index: 106

Text #8

Max Range: 3.7989. Min Range: -3.7989

Max Act: 3.7364. Min Act: -0.1700

Data Index: 372017 (C4 (Web Text))

Max Activating Token Index: 217

Text #9

Max Range: 3.7989. Min Range: -3.7989

Max Act: 3.7051. Min Act: -0.1700

Data Index: 950083 (C4 (Web Text))

Max Activating Token Index: 807

Text #10

Max Range: 3.7989. Min Range: -3.7989

Max Act: 3.7364. Min Act: -0.1700

Data Index: 905920 (C4 (Web Text))

Max Activating Token Index: 468

Text #11

Max Range: 3.7989. Min Range: -3.7989

Max Act: 3.7364. Min Act: -0.1700

Data Index: 1325605 (C4 (Web Text))

Max Activating Token Index: 493

Text #12

Max Range: 3.7989. Min Range: -3.7989

Max Act: 3.7677. Min Act: -0.1700

Data Index: 82097 (C4 (Web Text))

Max Activating Token Index: 142

Text #13

Max Range: 3.7989. Min Range: -3.7989

Max Act: 3.7051. Min Act: -0.1700

Data Index: 799040 (C4 (Web Text))

Max Activating Token Index: 272

Text #14

Max Range: 3.7989. Min Range: -3.7989

Max Act: 3.7364. Min Act: -0.1700

Data Index: 312413 (C4 (Web Text))

Max Activating Token Index: 754

Text #15

Max Range: 3.7989. Min Range: -3.7989

Max Act: 3.7677. Min Act: -0.1700

Data Index: 1163272 (C4 (Web Text))

Max Activating Token Index: 103

Text #16

Max Range: 3.7989. Min Range: -3.7989

Max Act: 3.7364. Min Act: -0.1700

Data Index: 515921 (C4 (Web Text))

Max Activating Token Index: 215

Text #17

Max Range: 3.7989. Min Range: -3.7989

Max Act: 3.7677. Min Act: -0.1700

Data Index: 1057671 (C4 (Web Text))

Max Activating Token Index: 138

Text #18

Max Range: 3.7989. Min Range: -3.7989

Max Act: 3.7364. Min Act: -0.1700

Data Index: 1024858 (C4 (Web Text))

Max Activating Token Index: 277

Text #19

Max Range: 3.7989. Min Range: -3.7989

Max Act: 3.7051. Min Act: -0.1700

Data Index: 172852 (C4 (Web Text))

Max Activating Token Index: 96