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

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

Neuron 349 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.8464. Min Range: -3.8464

Max Act: 3.8307. Min Act: -0.1700

Data Index: 936221 (C4 (Web Text))

Max Activating Token Index: 545

Text #1

Max Range: 3.8464. Min Range: -3.8464

Max Act: 3.8464. Min Act: -0.1700

Data Index: 43448 (C4 (Web Text))

Max Activating Token Index: 63

Text #2

Max Range: 3.8464. Min Range: -3.8464

Max Act: 3.8464. Min Act: -0.1700

Data Index: 228461 (C4 (Web Text))

Max Activating Token Index: 698

Text #3

Max Range: 3.8464. Min Range: -3.8464

Max Act: 3.8307. Min Act: -0.1700

Data Index: 1256262 (C4 (Web Text))

Max Activating Token Index: 1007

Text #4

Max Range: 3.8464. Min Range: -3.8464

Max Act: 3.8307. Min Act: -0.1700

Data Index: 806936 (C4 (Web Text))

Max Activating Token Index: 928

Text #5

Max Range: 3.8464. Min Range: -3.8464

Max Act: 3.8151. Min Act: -0.1700

Data Index: 35722 (C4 (Web Text))

Max Activating Token Index: 314

Text #6

Max Range: 3.8464. Min Range: -3.8464

Max Act: 3.8151. Min Act: -0.1700

Data Index: 1234274 (C4 (Web Text))

Max Activating Token Index: 533

Text #7

Max Range: 3.8464. Min Range: -3.8464

Max Act: 3.7525. Min Act: -0.1700

Data Index: 1097063 (C4 (Web Text))

Max Activating Token Index: 780

Text #8

Max Range: 3.8464. Min Range: -3.8464

Max Act: 3.7369. Min Act: -0.1700

Data Index: 761928 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 3.8464. Min Range: -3.8464

Max Act: 3.7525. Min Act: -0.1700

Data Index: 695091 (C4 (Web Text))

Max Activating Token Index: 759

Text #10

Max Range: 3.8464. Min Range: -3.8464

Max Act: 3.7525. Min Act: -0.1700

Data Index: 497577 (C4 (Web Text))

Max Activating Token Index: 460

Text #11

Max Range: 3.8464. Min Range: -3.8464

Max Act: 3.7525. Min Act: -0.1700

Data Index: 747296 (C4 (Web Text))

Max Activating Token Index: 158

Text #12

Max Range: 3.8464. Min Range: -3.8464

Max Act: 3.7369. Min Act: -0.1700

Data Index: 401167 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 3.8464. Min Range: -3.8464

Max Act: 3.7056. Min Act: -0.1700

Data Index: 156882 (C4 (Web Text))

Max Activating Token Index: 210

Text #14

Max Range: 3.8464. Min Range: -3.8464

Max Act: 3.7212. Min Act: -0.1700

Data Index: 488531 (C4 (Web Text))

Max Activating Token Index: 534

Text #15

Max Range: 3.8464. Min Range: -3.8464

Max Act: 3.7212. Min Act: -0.1700

Data Index: 1350949 (C4 (Web Text))

Max Activating Token Index: 951

Text #16

Max Range: 3.8464. Min Range: -3.8464

Max Act: 3.6899. Min Act: -0.1700

Data Index: 1041367 (C4 (Web Text))

Max Activating Token Index: 810

Text #17

Max Range: 3.8464. Min Range: -3.8464

Max Act: 3.6899. Min Act: -0.1700

Data Index: 1251111 (C4 (Web Text))

Max Activating Token Index: 190

Text #18

Max Range: 3.8464. Min Range: -3.8464

Max Act: 3.7056. Min Act: -0.1700

Data Index: 451244 (C4 (Web Text))

Max Activating Token Index: 745

Text #19

Max Range: 3.8464. Min Range: -3.8464

Max Act: 3.7056. Min Act: -0.1700

Data Index: 135455 (C4 (Web Text))

Max Activating Token Index: 750