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

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

Neuron 355 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3500. Min Range: -5.3500

Max Act: 5.3500. Min Act: -0.1700

Data Index: 1116348 (C4 (Web Text))

Max Activating Token Index: 1015

Text #1

Max Range: 5.3500. Min Range: -5.3500

Max Act: 5.2875. Min Act: -0.1700

Data Index: 228223 (C4 (Web Text))

Max Activating Token Index: 340

Text #2

Max Range: 5.3500. Min Range: -5.3500

Max Act: 5.3187. Min Act: -0.1700

Data Index: 386505 (C4 (Web Text))

Max Activating Token Index: 754

Text #3

Max Range: 5.3500. Min Range: -5.3500

Max Act: 5.2875. Min Act: -0.1700

Data Index: 1149165 (C4 (Web Text))

Max Activating Token Index: 345

Text #4

Max Range: 5.3500. Min Range: -5.3500

Max Act: 5.1937. Min Act: -0.1700

Data Index: 627611 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 5.3500. Min Range: -5.3500

Max Act: 5.1937. Min Act: -0.1700

Data Index: 885399 (C4 (Web Text))

Max Activating Token Index: 363

Text #6

Max Range: 5.3500. Min Range: -5.3500

Max Act: 5.1937. Min Act: -0.1700

Data Index: 1233438 (C4 (Web Text))

Max Activating Token Index: 970

Text #7

Max Range: 5.3500. Min Range: -5.3500

Max Act: 5.1937. Min Act: -0.1700

Data Index: 863407 (C4 (Web Text))

Max Activating Token Index: 998

Text #8

Max Range: 5.3500. Min Range: -5.3500

Max Act: 5.1625. Min Act: -0.1700

Data Index: 413407 (C4 (Web Text))

Max Activating Token Index: 311

Text #9

Max Range: 5.3500. Min Range: -5.3500

Max Act: 5.1312. Min Act: -0.1700

Data Index: 986657 (C4 (Web Text))

Max Activating Token Index: 909

Text #10

Max Range: 5.3500. Min Range: -5.3500

Max Act: 5.1625. Min Act: -0.1700

Data Index: 1294654 (C4 (Web Text))

Max Activating Token Index: 912

Text #11

Max Range: 5.3500. Min Range: -5.3500

Max Act: 5.1312. Min Act: -0.1700

Data Index: 1183284 (C4 (Web Text))

Max Activating Token Index: 724

Text #12

Max Range: 5.3500. Min Range: -5.3500

Max Act: 5.1000. Min Act: -0.1700

Data Index: 136745 (C4 (Web Text))

Max Activating Token Index: 923

Text #13

Max Range: 5.3500. Min Range: -5.3500

Max Act: 5.1000. Min Act: -0.1700

Data Index: 651241 (C4 (Web Text))

Max Activating Token Index: 697

Text #14

Max Range: 5.3500. Min Range: -5.3500

Max Act: 5.1312. Min Act: -0.1700

Data Index: 1353385 (C4 (Web Text))

Max Activating Token Index: 470

Text #15

Max Range: 5.3500. Min Range: -5.3500

Max Act: 5.1000. Min Act: -0.1700

Data Index: 421631 (C4 (Web Text))

Max Activating Token Index: 805

Text #16

Max Range: 5.3500. Min Range: -5.3500

Max Act: 5.1000. Min Act: -0.1700

Data Index: 355582 (C4 (Web Text))

Max Activating Token Index: 272

Text #17

Max Range: 5.3500. Min Range: -5.3500

Max Act: 5.1000. Min Act: -0.1700

Data Index: 864860 (C4 (Web Text))

Max Activating Token Index: 894

Text #18

Max Range: 5.3500. Min Range: -5.3500

Max Act: 5.1312. Min Act: -0.1700

Data Index: 524301 (C4 (Web Text))

Max Activating Token Index: 420

Text #19

Max Range: 5.3500. Min Range: -5.3500

Max Act: 5.1000. Min Act: -0.1700

Data Index: 289122 (C4 (Web Text))

Max Activating Token Index: 971