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

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

Neuron 433 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: 3.3676. Min Range: -3.3676

Max Act: 3.3656. Min Act: -0.1700

Data Index: 601631 (C4 (Web Text))

Max Activating Token Index: 161

Text #1

Max Range: 3.3676. Min Range: -3.3676

Max Act: 3.3676. Min Act: -0.1700

Data Index: 408498 (C4 (Web Text))

Max Activating Token Index: 529

Text #2

Max Range: 3.3676. Min Range: -3.3676

Max Act: 3.3527. Min Act: -0.1700

Data Index: 679954 (C4 (Web Text))

Max Activating Token Index: 626

Text #3

Max Range: 3.3676. Min Range: -3.3676

Max Act: 3.3272. Min Act: -0.1700

Data Index: 289052 (C4 (Web Text))

Max Activating Token Index: 658

Text #4

Max Range: 3.3676. Min Range: -3.3676

Max Act: 3.3345. Min Act: -0.1699

Data Index: 112554 (C4 (Web Text))

Max Activating Token Index: 946

Text #5

Max Range: 3.3676. Min Range: -3.3676

Max Act: 3.3263. Min Act: -0.1700

Data Index: 1118987 (C4 (Web Text))

Max Activating Token Index: 583

Text #6

Max Range: 3.3676. Min Range: -3.3676

Max Act: 3.3356. Min Act: -0.1700

Data Index: 99254 (C4 (Web Text))

Max Activating Token Index: 35

Text #7

Max Range: 3.3676. Min Range: -3.3676

Max Act: 3.3311. Min Act: -0.1700

Data Index: 1084188 (C4 (Web Text))

Max Activating Token Index: 793

Text #8

Max Range: 3.3676. Min Range: -3.3676

Max Act: 3.3159. Min Act: -0.1700

Data Index: 182977 (C4 (Web Text))

Max Activating Token Index: 373

Text #9

Max Range: 3.3676. Min Range: -3.3676

Max Act: 3.3300. Min Act: -0.1700

Data Index: 979942 (C4 (Web Text))

Max Activating Token Index: 255

Text #10

Max Range: 3.3676. Min Range: -3.3676

Max Act: 3.3168. Min Act: -0.1700

Data Index: 1287826 (C4 (Web Text))

Max Activating Token Index: 356

Text #11

Max Range: 3.3676. Min Range: -3.3676

Max Act: 3.3268. Min Act: -0.1700

Data Index: 427084 (C4 (Web Text))

Max Activating Token Index: 222

Text #12

Max Range: 3.3676. Min Range: -3.3676

Max Act: 3.3123. Min Act: -0.1700

Data Index: 822058 (C4 (Web Text))

Max Activating Token Index: 399

Text #13

Max Range: 3.3676. Min Range: -3.3676

Max Act: 3.3128. Min Act: -0.1700

Data Index: 933668 (C4 (Web Text))

Max Activating Token Index: 1009

Text #14

Max Range: 3.3676. Min Range: -3.3676

Max Act: 3.2952. Min Act: -0.1700

Data Index: 617813 (C4 (Web Text))

Max Activating Token Index: 677

Text #15

Max Range: 3.3676. Min Range: -3.3676

Max Act: 3.3189. Min Act: -0.1700

Data Index: 1065490 (C4 (Web Text))

Max Activating Token Index: 774

Text #16

Max Range: 3.3676. Min Range: -3.3676

Max Act: 3.2899. Min Act: -0.1700

Data Index: 892014 (C4 (Web Text))

Max Activating Token Index: 75

Text #17

Max Range: 3.3676. Min Range: -3.3676

Max Act: 3.2703. Min Act: -0.1700

Data Index: 738234 (C4 (Web Text))

Max Activating Token Index: 107

Text #18

Max Range: 3.3676. Min Range: -3.3676

Max Act: 3.2892. Min Act: -0.1700

Data Index: 716317 (C4 (Web Text))

Max Activating Token Index: 1006

Text #19

Max Range: 3.3676. Min Range: -3.3676

Max Act: 3.2742. Min Act: -0.1700

Data Index: 689700 (C4 (Web Text))

Max Activating Token Index: 546