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

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

Neuron 1232 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7958. Min Range: -5.7958

Max Act: 5.7958. Min Act: -0.1700

Data Index: 1224000 (C4 (Web Text))

Max Activating Token Index: 1018

Text #1

Max Range: 5.7958. Min Range: -5.7958

Max Act: 5.2333. Min Act: -0.1700

Data Index: 186565 (C4 (Web Text))

Max Activating Token Index: 998

Text #2

Max Range: 5.7958. Min Range: -5.7958

Max Act: 5.1083. Min Act: -0.1700

Data Index: 61768 (C4 (Web Text))

Max Activating Token Index: 647

Text #3

Max Range: 5.7958. Min Range: -5.7958

Max Act: 5.1083. Min Act: -0.1700

Data Index: 1310728 (C4 (Web Text))

Max Activating Token Index: 397

Text #4

Max Range: 5.7958. Min Range: -5.7958

Max Act: 5.1396. Min Act: -0.1700

Data Index: 296761 (C4 (Web Text))

Max Activating Token Index: 89

Text #5

Max Range: 5.7958. Min Range: -5.7958

Max Act: 5.1083. Min Act: -0.1700

Data Index: 295969 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 5.7958. Min Range: -5.7958

Max Act: 5.0771. Min Act: -0.1700

Data Index: 1290219 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 5.7958. Min Range: -5.7958

Max Act: 5.0458. Min Act: -0.1700

Data Index: 554155 (C4 (Web Text))

Max Activating Token Index: 989

Text #8

Max Range: 5.7958. Min Range: -5.7958

Max Act: 5.0146. Min Act: -0.1700

Data Index: 735122 (C4 (Web Text))

Max Activating Token Index: 843

Text #9

Max Range: 5.7958. Min Range: -5.7958

Max Act: 5.0458. Min Act: -0.1700

Data Index: 913342 (C4 (Web Text))

Max Activating Token Index: 460

Text #10

Max Range: 5.7958. Min Range: -5.7958

Max Act: 4.9833. Min Act: -0.1700

Data Index: 985756 (C4 (Web Text))

Max Activating Token Index: 401

Text #11

Max Range: 5.7958. Min Range: -5.7958

Max Act: 4.9833. Min Act: -0.1700

Data Index: 805333 (C4 (Web Text))

Max Activating Token Index: 703

Text #12

Max Range: 5.7958. Min Range: -5.7958

Max Act: 4.9208. Min Act: -0.1700

Data Index: 1259345 (C4 (Web Text))

Max Activating Token Index: 268

Text #13

Max Range: 5.7958. Min Range: -5.7958

Max Act: 4.9521. Min Act: -0.1700

Data Index: 267985 (C4 (Web Text))

Max Activating Token Index: 886

Text #14

Max Range: 5.7958. Min Range: -5.7958

Max Act: 4.9521. Min Act: -0.1700

Data Index: 179570 (C4 (Web Text))

Max Activating Token Index: 235

Text #15

Max Range: 5.7958. Min Range: -5.7958

Max Act: 4.9833. Min Act: -0.1700

Data Index: 625891 (C4 (Web Text))

Max Activating Token Index: 470

Text #16

Max Range: 5.7958. Min Range: -5.7958

Max Act: 4.9521. Min Act: -0.1700

Data Index: 1011470 (C4 (Web Text))

Max Activating Token Index: 323

Text #17

Max Range: 5.7958. Min Range: -5.7958

Max Act: 4.9521. Min Act: -0.1700

Data Index: 890117 (C4 (Web Text))

Max Activating Token Index: 189

Text #18

Max Range: 5.7958. Min Range: -5.7958

Max Act: 4.9521. Min Act: -0.1700

Data Index: 587248 (C4 (Web Text))

Max Activating Token Index: 600

Text #19

Max Range: 5.7958. Min Range: -5.7958

Max Act: 4.9521. Min Act: -0.1700

Data Index: 1137982 (C4 (Web Text))

Max Activating Token Index: 244