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

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

Neuron 1956 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9462. Min Range: -3.9462

Max Act: 3.9462. Min Act: -0.1700

Data Index: 1111992 (C4 (Web Text))

Max Activating Token Index: 267

Text #1

Max Range: 3.9462. Min Range: -3.9462

Max Act: 3.9149. Min Act: -0.1700

Data Index: 821719 (C4 (Web Text))

Max Activating Token Index: 100

Text #2

Max Range: 3.9462. Min Range: -3.9462

Max Act: 3.8524. Min Act: -0.1700

Data Index: 1088076 (C4 (Web Text))

Max Activating Token Index: 743

Text #3

Max Range: 3.9462. Min Range: -3.9462

Max Act: 3.8211. Min Act: -0.1700

Data Index: 610690 (C4 (Web Text))

Max Activating Token Index: 146

Text #4

Max Range: 3.9462. Min Range: -3.9462

Max Act: 3.7898. Min Act: -0.1700

Data Index: 606051 (C4 (Web Text))

Max Activating Token Index: 297

Text #5

Max Range: 3.9462. Min Range: -3.9462

Max Act: 3.7898. Min Act: -0.1700

Data Index: 1170691 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 3.9462. Min Range: -3.9462

Max Act: 3.7898. Min Act: -0.1700

Data Index: 619754 (C4 (Web Text))

Max Activating Token Index: 628

Text #7

Max Range: 3.9462. Min Range: -3.9462

Max Act: 3.7898. Min Act: -0.1700

Data Index: 483728 (C4 (Web Text))

Max Activating Token Index: 559

Text #8

Max Range: 3.9462. Min Range: -3.9462

Max Act: 3.7272. Min Act: -0.1700

Data Index: 282692 (C4 (Web Text))

Max Activating Token Index: 170

Text #9

Max Range: 3.9462. Min Range: -3.9462

Max Act: 3.7272. Min Act: -0.1700

Data Index: 1259273 (C4 (Web Text))

Max Activating Token Index: 144

Text #10

Max Range: 3.9462. Min Range: -3.9462

Max Act: 3.7272. Min Act: -0.1700

Data Index: 389315 (C4 (Web Text))

Max Activating Token Index: 979

Text #11

Max Range: 3.9462. Min Range: -3.9462

Max Act: 3.7272. Min Act: -0.1700

Data Index: 720619 (C4 (Web Text))

Max Activating Token Index: 361

Text #12

Max Range: 3.9462. Min Range: -3.9462

Max Act: 3.6959. Min Act: -0.1700

Data Index: 338494 (C4 (Web Text))

Max Activating Token Index: 442

Text #13

Max Range: 3.9462. Min Range: -3.9462

Max Act: 3.6959. Min Act: -0.1700

Data Index: 313690 (C4 (Web Text))

Max Activating Token Index: 262

Text #14

Max Range: 3.9462. Min Range: -3.9462

Max Act: 3.6646. Min Act: -0.1700

Data Index: 130070 (C4 (Web Text))

Max Activating Token Index: 5

Text #15

Max Range: 3.9462. Min Range: -3.9462

Max Act: 3.6646. Min Act: -0.1700

Data Index: 1290400 (C4 (Web Text))

Max Activating Token Index: 408

Text #16

Max Range: 3.9462. Min Range: -3.9462

Max Act: 3.6333. Min Act: -0.1700

Data Index: 580623 (C4 (Web Text))

Max Activating Token Index: 428

Text #17

Max Range: 3.9462. Min Range: -3.9462

Max Act: 3.6646. Min Act: -0.1700

Data Index: 826739 (C4 (Web Text))

Max Activating Token Index: 965

Text #18

Max Range: 3.9462. Min Range: -3.9462

Max Act: 3.6646. Min Act: -0.1700

Data Index: 1118552 (C4 (Web Text))

Max Activating Token Index: 621

Text #19

Max Range: 3.9462. Min Range: -3.9462

Max Act: 3.6020. Min Act: -0.1700

Data Index: 852678 (C4 (Web Text))

Max Activating Token Index: 304