Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 160 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.4900. Min Range: -3.4900

Max Act: 3.4900. Min Act: -0.1700

Data Index: 1145036 (C4 (Web Text))

Max Activating Token Index: 574

Text #1

Max Range: 3.4900. Min Range: -3.4900

Max Act: 3.4583. Min Act: -0.1700

Data Index: 446190 (C4 (Web Text))

Max Activating Token Index: 520

Text #2

Max Range: 3.4900. Min Range: -3.4900

Max Act: 3.3236. Min Act: -0.1700

Data Index: 1112696 (C4 (Web Text))

Max Activating Token Index: 795

Text #3

Max Range: 3.4900. Min Range: -3.4900

Max Act: 3.3358. Min Act: -0.1700

Data Index: 1137551 (C4 (Web Text))

Max Activating Token Index: 817

Text #4

Max Range: 3.4900. Min Range: -3.4900

Max Act: 3.3773. Min Act: -0.1700

Data Index: 1630055 (Python Code)

Max Activating Token Index: 571

Text #5

Max Range: 3.4900. Min Range: -3.4900

Max Act: 3.3133. Min Act: -0.1700

Data Index: 846299 (C4 (Web Text))

Max Activating Token Index: 785

Text #6

Max Range: 3.4900. Min Range: -3.4900

Max Act: 3.3199. Min Act: -0.1700

Data Index: 1230551 (C4 (Web Text))

Max Activating Token Index: 899

Text #7

Max Range: 3.4900. Min Range: -3.4900

Max Act: 3.2822. Min Act: -0.1700

Data Index: 1519858 (Python Code)

Max Activating Token Index: 908

Text #8

Max Range: 3.4900. Min Range: -3.4900

Max Act: 3.3057. Min Act: -0.1700

Data Index: 696357 (C4 (Web Text))

Max Activating Token Index: 318

Text #9

Max Range: 3.4900. Min Range: -3.4900

Max Act: 3.2953. Min Act: -0.1700

Data Index: 98201 (C4 (Web Text))

Max Activating Token Index: 992

Text #10

Max Range: 3.4900. Min Range: -3.4900

Max Act: 3.2576. Min Act: -0.1700

Data Index: 1344119 (C4 (Web Text))

Max Activating Token Index: 867

Text #11

Max Range: 3.4900. Min Range: -3.4900

Max Act: 3.3024. Min Act: -0.1700

Data Index: 1237348 (C4 (Web Text))

Max Activating Token Index: 977

Text #12

Max Range: 3.4900. Min Range: -3.4900

Max Act: 3.2433. Min Act: -0.1700

Data Index: 1612788 (Python Code)

Max Activating Token Index: 135

Text #13

Max Range: 3.4900. Min Range: -3.4900

Max Act: 3.2258. Min Act: -0.1700

Data Index: 658974 (C4 (Web Text))

Max Activating Token Index: 160

Text #14

Max Range: 3.4900. Min Range: -3.4900

Max Act: 3.2107. Min Act: -0.1700

Data Index: 1411647 (Python Code)

Max Activating Token Index: 305

Text #15

Max Range: 3.4900. Min Range: -3.4900

Max Act: 3.2247. Min Act: -0.1700

Data Index: 945384 (C4 (Web Text))

Max Activating Token Index: 907

Text #16

Max Range: 3.4900. Min Range: -3.4900

Max Act: 3.1711. Min Act: -0.1700

Data Index: 1607209 (Python Code)

Max Activating Token Index: 754

Text #17

Max Range: 3.4900. Min Range: -3.4900

Max Act: 3.1871. Min Act: -0.1700

Data Index: 1632593 (Python Code)

Max Activating Token Index: 44

Text #18

Max Range: 3.4900. Min Range: -3.4900

Max Act: 3.2470. Min Act: -0.1700

Data Index: 1579273 (Python Code)

Max Activating Token Index: 1007

Text #19

Max Range: 3.4900. Min Range: -3.4900

Max Act: 3.2280. Min Act: -0.1700

Data Index: 1329946 (C4 (Web Text))

Max Activating Token Index: 451