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

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

Neuron 841 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4665. Min Range: -3.4665

Max Act: 3.4665. Min Act: -0.1700

Data Index: 1562478 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 3.4665. Min Range: -3.4665

Max Act: 3.4194. Min Act: -0.1700

Data Index: 1575970 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 3.4665. Min Range: -3.4665

Max Act: 3.3410. Min Act: -0.1700

Data Index: 1313014 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 3.4665. Min Range: -3.4665

Max Act: 3.3253. Min Act: -0.1700

Data Index: 1315867 (C4 (Web Text))

Max Activating Token Index: 384

Text #4

Max Range: 3.4665. Min Range: -3.4665

Max Act: 3.3096. Min Act: -0.1700

Data Index: 901438 (C4 (Web Text))

Max Activating Token Index: 4

Text #5

Max Range: 3.4665. Min Range: -3.4665

Max Act: 3.2939. Min Act: -0.1700

Data Index: 606415 (C4 (Web Text))

Max Activating Token Index: 109

Text #6

Max Range: 3.4665. Min Range: -3.4665

Max Act: 3.2782. Min Act: -0.1700

Data Index: 320658 (C4 (Web Text))

Max Activating Token Index: 1003

Text #7

Max Range: 3.4665. Min Range: -3.4665

Max Act: 3.2782. Min Act: -0.1700

Data Index: 920491 (C4 (Web Text))

Max Activating Token Index: 19

Text #8

Max Range: 3.4665. Min Range: -3.4665

Max Act: 3.2625. Min Act: -0.1700

Data Index: 359289 (C4 (Web Text))

Max Activating Token Index: 338

Text #9

Max Range: 3.4665. Min Range: -3.4665

Max Act: 3.2625. Min Act: -0.1700

Data Index: 540785 (C4 (Web Text))

Max Activating Token Index: 828

Text #10

Max Range: 3.4665. Min Range: -3.4665

Max Act: 3.2625. Min Act: -0.1700

Data Index: 614239 (C4 (Web Text))

Max Activating Token Index: 5

Text #11

Max Range: 3.4665. Min Range: -3.4665

Max Act: 3.2625. Min Act: -0.1700

Data Index: 573544 (C4 (Web Text))

Max Activating Token Index: 102

Text #12

Max Range: 3.4665. Min Range: -3.4665

Max Act: 3.2153. Min Act: -0.1700

Data Index: 16028 (C4 (Web Text))

Max Activating Token Index: 749

Text #13

Max Range: 3.4665. Min Range: -3.4665

Max Act: 3.2468. Min Act: -0.1700

Data Index: 765218 (C4 (Web Text))

Max Activating Token Index: 434

Text #14

Max Range: 3.4665. Min Range: -3.4665

Max Act: 3.2468. Min Act: -0.1700

Data Index: 402107 (C4 (Web Text))

Max Activating Token Index: 978

Text #15

Max Range: 3.4665. Min Range: -3.4665

Max Act: 3.2153. Min Act: -0.1700

Data Index: 570161 (C4 (Web Text))

Max Activating Token Index: 741

Text #16

Max Range: 3.4665. Min Range: -3.4665

Max Act: 3.2468. Min Act: -0.1700

Data Index: 1288866 (C4 (Web Text))

Max Activating Token Index: 139

Text #17

Max Range: 3.4665. Min Range: -3.4665

Max Act: 3.1996. Min Act: -0.1700

Data Index: 1327682 (C4 (Web Text))

Max Activating Token Index: 400

Text #18

Max Range: 3.4665. Min Range: -3.4665

Max Act: 3.2153. Min Act: -0.1700

Data Index: 1325327 (C4 (Web Text))

Max Activating Token Index: 259

Text #19

Max Range: 3.4665. Min Range: -3.4665

Max Act: 3.2310. Min Act: -0.1700

Data Index: 380919 (C4 (Web Text))

Max Activating Token Index: 3