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

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

Neuron 1676 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2108. Min Range: -3.2108

Max Act: 3.2108. Min Act: -0.1700

Data Index: 136037 (C4 (Web Text))

Max Activating Token Index: 811

Text #1

Max Range: 3.2108. Min Range: -3.2108

Max Act: 3.1321. Min Act: -0.1700

Data Index: 282385 (C4 (Web Text))

Max Activating Token Index: 942

Text #2

Max Range: 3.2108. Min Range: -3.2108

Max Act: 3.0690. Min Act: -0.1700

Data Index: 689001 (C4 (Web Text))

Max Activating Token Index: 452

Text #3

Max Range: 3.2108. Min Range: -3.2108

Max Act: 3.0848. Min Act: -0.1700

Data Index: 1208586 (C4 (Web Text))

Max Activating Token Index: 363

Text #4

Max Range: 3.2108. Min Range: -3.2108

Max Act: 3.0217. Min Act: -0.1700

Data Index: 708325 (C4 (Web Text))

Max Activating Token Index: 378

Text #5

Max Range: 3.2108. Min Range: -3.2108

Max Act: 3.0533. Min Act: -0.1700

Data Index: 777455 (C4 (Web Text))

Max Activating Token Index: 318

Text #6

Max Range: 3.2108. Min Range: -3.2108

Max Act: 3.0217. Min Act: -0.1700

Data Index: 919231 (C4 (Web Text))

Max Activating Token Index: 132

Text #7

Max Range: 3.2108. Min Range: -3.2108

Max Act: 3.0375. Min Act: -0.1700

Data Index: 1006936 (C4 (Web Text))

Max Activating Token Index: 665

Text #8

Max Range: 3.2108. Min Range: -3.2108

Max Act: 3.0690. Min Act: -0.1700

Data Index: 788093 (C4 (Web Text))

Max Activating Token Index: 958

Text #9

Max Range: 3.2108. Min Range: -3.2108

Max Act: 3.1006. Min Act: -0.1700

Data Index: 215839 (C4 (Web Text))

Max Activating Token Index: 989

Text #10

Max Range: 3.2108. Min Range: -3.2108

Max Act: 3.0217. Min Act: -0.1700

Data Index: 412061 (C4 (Web Text))

Max Activating Token Index: 620

Text #11

Max Range: 3.2108. Min Range: -3.2108

Max Act: 3.0217. Min Act: -0.1700

Data Index: 788451 (C4 (Web Text))

Max Activating Token Index: 477

Text #12

Max Range: 3.2108. Min Range: -3.2108

Max Act: 3.0059. Min Act: -0.1700

Data Index: 1136439 (C4 (Web Text))

Max Activating Token Index: 97

Text #13

Max Range: 3.2108. Min Range: -3.2108

Max Act: 3.0217. Min Act: -0.1700

Data Index: 581959 (C4 (Web Text))

Max Activating Token Index: 977

Text #14

Max Range: 3.2108. Min Range: -3.2108

Max Act: 2.9742. Min Act: -0.1700

Data Index: 318878 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 3.2108. Min Range: -3.2108

Max Act: 2.9109. Min Act: -0.1700

Data Index: 603486 (C4 (Web Text))

Max Activating Token Index: 599

Text #16

Max Range: 3.2108. Min Range: -3.2108

Max Act: 2.9426. Min Act: -0.1700

Data Index: 898762 (C4 (Web Text))

Max Activating Token Index: 351

Text #17

Max Range: 3.2108. Min Range: -3.2108

Max Act: 2.9742. Min Act: -0.1700

Data Index: 665818 (C4 (Web Text))

Max Activating Token Index: 564

Text #18

Max Range: 3.2108. Min Range: -3.2108

Max Act: 2.9584. Min Act: -0.1700

Data Index: 653154 (C4 (Web Text))

Max Activating Token Index: 815

Text #19

Max Range: 3.2108. Min Range: -3.2108

Max Act: 2.9109. Min Act: -0.1700

Data Index: 1013373 (C4 (Web Text))

Max Activating Token Index: 1023