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

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

Neuron 555 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5604. Min Range: -3.5604

Max Act: 3.5604. Min Act: -0.1700

Data Index: 47056 (C4 (Web Text))

Max Activating Token Index: 350

Text #1

Max Range: 3.5604. Min Range: -3.5604

Max Act: 3.5291. Min Act: -0.1700

Data Index: 1541970 (Python Code)

Max Activating Token Index: 725

Text #2

Max Range: 3.5604. Min Range: -3.5604

Max Act: 3.4664. Min Act: -0.1700

Data Index: 1330355 (C4 (Web Text))

Max Activating Token Index: 789

Text #3

Max Range: 3.5604. Min Range: -3.5604

Max Act: 3.4037. Min Act: -0.1700

Data Index: 448660 (C4 (Web Text))

Max Activating Token Index: 441

Text #4

Max Range: 3.5604. Min Range: -3.5604

Max Act: 3.4193. Min Act: -0.1700

Data Index: 705605 (C4 (Web Text))

Max Activating Token Index: 526

Text #5

Max Range: 3.5604. Min Range: -3.5604

Max Act: 3.4193. Min Act: -0.1700

Data Index: 327156 (C4 (Web Text))

Max Activating Token Index: 256

Text #6

Max Range: 3.5604. Min Range: -3.5604

Max Act: 3.4037. Min Act: -0.1700

Data Index: 375490 (C4 (Web Text))

Max Activating Token Index: 270

Text #7

Max Range: 3.5604. Min Range: -3.5604

Max Act: 3.3566. Min Act: -0.1700

Data Index: 227459 (C4 (Web Text))

Max Activating Token Index: 544

Text #8

Max Range: 3.5604. Min Range: -3.5604

Max Act: 3.3409. Min Act: -0.1700

Data Index: 300145 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 3.5604. Min Range: -3.5604

Max Act: 3.3252. Min Act: -0.1700

Data Index: 155310 (C4 (Web Text))

Max Activating Token Index: 321

Text #10

Max Range: 3.5604. Min Range: -3.5604

Max Act: 3.3409. Min Act: -0.1700

Data Index: 945403 (C4 (Web Text))

Max Activating Token Index: 364

Text #11

Max Range: 3.5604. Min Range: -3.5604

Max Act: 3.3409. Min Act: -0.1700

Data Index: 1214885 (C4 (Web Text))

Max Activating Token Index: 447

Text #12

Max Range: 3.5604. Min Range: -3.5604

Max Act: 3.3252. Min Act: -0.1700

Data Index: 1152998 (C4 (Web Text))

Max Activating Token Index: 896

Text #13

Max Range: 3.5604. Min Range: -3.5604

Max Act: 3.3252. Min Act: -0.1700

Data Index: 1131816 (C4 (Web Text))

Max Activating Token Index: 523

Text #14

Max Range: 3.5604. Min Range: -3.5604

Max Act: 3.3095. Min Act: -0.1700

Data Index: 1152462 (C4 (Web Text))

Max Activating Token Index: 587

Text #15

Max Range: 3.5604. Min Range: -3.5604

Max Act: 3.2624. Min Act: -0.1700

Data Index: 380382 (C4 (Web Text))

Max Activating Token Index: 708

Text #16

Max Range: 3.5604. Min Range: -3.5604

Max Act: 3.2938. Min Act: -0.1700

Data Index: 1259190 (C4 (Web Text))

Max Activating Token Index: 84

Text #17

Max Range: 3.5604. Min Range: -3.5604

Max Act: 3.3409. Min Act: -0.1700

Data Index: 991194 (C4 (Web Text))

Max Activating Token Index: 240

Text #18

Max Range: 3.5604. Min Range: -3.5604

Max Act: 3.2309. Min Act: -0.1700

Data Index: 118219 (C4 (Web Text))

Max Activating Token Index: 217

Text #19

Max Range: 3.5604. Min Range: -3.5604

Max Act: 3.2624. Min Act: -0.1700

Data Index: 465368 (C4 (Web Text))

Max Activating Token Index: 416