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

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

Neuron 1859 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3337. Min Range: -3.3337

Max Act: 3.3337. Min Act: -0.1700

Data Index: 521939 (C4 (Web Text))

Max Activating Token Index: 546

Text #1

Max Range: 3.3337. Min Range: -3.3337

Max Act: 3.2866. Min Act: -0.1700

Data Index: 298580 (C4 (Web Text))

Max Activating Token Index: 412

Text #2

Max Range: 3.3337. Min Range: -3.3337

Max Act: 3.3180. Min Act: -0.1700

Data Index: 155429 (C4 (Web Text))

Max Activating Token Index: 941

Text #3

Max Range: 3.3337. Min Range: -3.3337

Max Act: 3.2238. Min Act: -0.1700

Data Index: 341337 (C4 (Web Text))

Max Activating Token Index: 396

Text #4

Max Range: 3.3337. Min Range: -3.3337

Max Act: 3.1608. Min Act: -0.1700

Data Index: 77530 (C4 (Web Text))

Max Activating Token Index: 821

Text #5

Max Range: 3.3337. Min Range: -3.3337

Max Act: 3.1923. Min Act: -0.1700

Data Index: 795019 (C4 (Web Text))

Max Activating Token Index: 480

Text #6

Max Range: 3.3337. Min Range: -3.3337

Max Act: 3.1293. Min Act: -0.1700

Data Index: 1214621 (C4 (Web Text))

Max Activating Token Index: 363

Text #7

Max Range: 3.3337. Min Range: -3.3337

Max Act: 3.1608. Min Act: -0.1700

Data Index: 1107998 (C4 (Web Text))

Max Activating Token Index: 456

Text #8

Max Range: 3.3337. Min Range: -3.3337

Max Act: 3.2238. Min Act: -0.1700

Data Index: 1085029 (C4 (Web Text))

Max Activating Token Index: 885

Text #9

Max Range: 3.3337. Min Range: -3.3337

Max Act: 3.1766. Min Act: -0.1700

Data Index: 1169467 (C4 (Web Text))

Max Activating Token Index: 384

Text #10

Max Range: 3.3337. Min Range: -3.3337

Max Act: 3.1766. Min Act: -0.1700

Data Index: 588703 (C4 (Web Text))

Max Activating Token Index: 959

Text #11

Max Range: 3.3337. Min Range: -3.3337

Max Act: 3.1923. Min Act: -0.1700

Data Index: 920108 (C4 (Web Text))

Max Activating Token Index: 518

Text #12

Max Range: 3.3337. Min Range: -3.3337

Max Act: 3.1451. Min Act: -0.1700

Data Index: 1112337 (C4 (Web Text))

Max Activating Token Index: 238

Text #13

Max Range: 3.3337. Min Range: -3.3337

Max Act: 3.1451. Min Act: -0.1700

Data Index: 396448 (C4 (Web Text))

Max Activating Token Index: 486

Text #14

Max Range: 3.3337. Min Range: -3.3337

Max Act: 3.1451. Min Act: -0.1700

Data Index: 1051625 (C4 (Web Text))

Max Activating Token Index: 242

Text #15

Max Range: 3.3337. Min Range: -3.3337

Max Act: 3.1451. Min Act: -0.1700

Data Index: 513629 (C4 (Web Text))

Max Activating Token Index: 633

Text #16

Max Range: 3.3337. Min Range: -3.3337

Max Act: 3.1451. Min Act: -0.1700

Data Index: 695985 (C4 (Web Text))

Max Activating Token Index: 117

Text #17

Max Range: 3.3337. Min Range: -3.3337

Max Act: 3.1293. Min Act: -0.1700

Data Index: 555567 (C4 (Web Text))

Max Activating Token Index: 121

Text #18

Max Range: 3.3337. Min Range: -3.3337

Max Act: 3.1293. Min Act: -0.1700

Data Index: 1030654 (C4 (Web Text))

Max Activating Token Index: 702

Text #19

Max Range: 3.3337. Min Range: -3.3337

Max Act: 3.1136. Min Act: -0.1700

Data Index: 908749 (C4 (Web Text))

Max Activating Token Index: 795