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

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

Neuron 427 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: 3.9386. Min Range: -3.9386

Max Act: 3.9386. Min Act: -0.1700

Data Index: 65394 (C4 (Web Text))

Max Activating Token Index: 347

Text #1

Max Range: 3.9386. Min Range: -3.9386

Max Act: 3.9074. Min Act: -0.1700

Data Index: 1091364 (C4 (Web Text))

Max Activating Token Index: 716

Text #2

Max Range: 3.9386. Min Range: -3.9386

Max Act: 3.8448. Min Act: -0.1700

Data Index: 288956 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 3.9386. Min Range: -3.9386

Max Act: 3.8605. Min Act: -0.1700

Data Index: 72489 (C4 (Web Text))

Max Activating Token Index: 114

Text #4

Max Range: 3.9386. Min Range: -3.9386

Max Act: 3.8292. Min Act: -0.1700

Data Index: 1173933 (C4 (Web Text))

Max Activating Token Index: 189

Text #5

Max Range: 3.9386. Min Range: -3.9386

Max Act: 3.8135. Min Act: -0.1700

Data Index: 1200239 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 3.9386. Min Range: -3.9386

Max Act: 3.7823. Min Act: -0.1700

Data Index: 285583 (C4 (Web Text))

Max Activating Token Index: 306

Text #7

Max Range: 3.9386. Min Range: -3.9386

Max Act: 3.7510. Min Act: -0.1700

Data Index: 666151 (C4 (Web Text))

Max Activating Token Index: 392

Text #8

Max Range: 3.9386. Min Range: -3.9386

Max Act: 3.7823. Min Act: -0.1700

Data Index: 1010808 (C4 (Web Text))

Max Activating Token Index: 454

Text #9

Max Range: 3.9386. Min Range: -3.9386

Max Act: 3.6727. Min Act: -0.1700

Data Index: 679150 (C4 (Web Text))

Max Activating Token Index: 185

Text #10

Max Range: 3.9386. Min Range: -3.9386

Max Act: 3.7353. Min Act: -0.1700

Data Index: 577430 (C4 (Web Text))

Max Activating Token Index: 777

Text #11

Max Range: 3.9386. Min Range: -3.9386

Max Act: 3.7040. Min Act: -0.1700

Data Index: 884442 (C4 (Web Text))

Max Activating Token Index: 449

Text #12

Max Range: 3.9386. Min Range: -3.9386

Max Act: 3.7197. Min Act: -0.1700

Data Index: 1352546 (C4 (Web Text))

Max Activating Token Index: 353

Text #13

Max Range: 3.9386. Min Range: -3.9386

Max Act: 3.6884. Min Act: -0.1700

Data Index: 394801 (C4 (Web Text))

Max Activating Token Index: 189

Text #14

Max Range: 3.9386. Min Range: -3.9386

Max Act: 3.6884. Min Act: -0.1700

Data Index: 478779 (C4 (Web Text))

Max Activating Token Index: 655

Text #15

Max Range: 3.9386. Min Range: -3.9386

Max Act: 3.6414. Min Act: -0.1700

Data Index: 242975 (C4 (Web Text))

Max Activating Token Index: 159

Text #16

Max Range: 3.9386. Min Range: -3.9386

Max Act: 3.6414. Min Act: -0.1700

Data Index: 1220035 (C4 (Web Text))

Max Activating Token Index: 327

Text #17

Max Range: 3.9386. Min Range: -3.9386

Max Act: 3.6571. Min Act: -0.1700

Data Index: 490133 (C4 (Web Text))

Max Activating Token Index: 37

Text #18

Max Range: 3.9386. Min Range: -3.9386

Max Act: 3.6414. Min Act: -0.1700

Data Index: 828763 (C4 (Web Text))

Max Activating Token Index: 821

Text #19

Max Range: 3.9386. Min Range: -3.9386

Max Act: 3.6414. Min Act: -0.1700

Data Index: 108498 (C4 (Web Text))

Max Activating Token Index: 358