Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1275 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.4126. Min Range: -3.4126

Max Act: 3.4126. Min Act: -0.1700

Data Index: 63980 (C4 (Web Text))

Max Activating Token Index: 447

Text #1

Max Range: 3.4126. Min Range: -3.4126

Max Act: 3.2399. Min Act: -0.1700

Data Index: 685750 (C4 (Web Text))

Max Activating Token Index: 819

Text #2

Max Range: 3.4126. Min Range: -3.4126

Max Act: 3.1770. Min Act: -0.1700

Data Index: 1082473 (C4 (Web Text))

Max Activating Token Index: 678

Text #3

Max Range: 3.4126. Min Range: -3.4126

Max Act: 3.2085. Min Act: -0.1700

Data Index: 876283 (C4 (Web Text))

Max Activating Token Index: 862

Text #4

Max Range: 3.4126. Min Range: -3.4126

Max Act: 3.1612. Min Act: -0.1700

Data Index: 895157 (C4 (Web Text))

Max Activating Token Index: 137

Text #5

Max Range: 3.4126. Min Range: -3.4126

Max Act: 3.1455. Min Act: -0.1700

Data Index: 267029 (C4 (Web Text))

Max Activating Token Index: 586

Text #6

Max Range: 3.4126. Min Range: -3.4126

Max Act: 3.1927. Min Act: -0.1700

Data Index: 1018379 (C4 (Web Text))

Max Activating Token Index: 928

Text #7

Max Range: 3.4126. Min Range: -3.4126

Max Act: 3.1455. Min Act: -0.1700

Data Index: 437446 (C4 (Web Text))

Max Activating Token Index: 417

Text #8

Max Range: 3.4126. Min Range: -3.4126

Max Act: 3.0824. Min Act: -0.1700

Data Index: 591457 (C4 (Web Text))

Max Activating Token Index: 335

Text #9

Max Range: 3.4126. Min Range: -3.4126

Max Act: 3.1455. Min Act: -0.1700

Data Index: 272625 (C4 (Web Text))

Max Activating Token Index: 658

Text #10

Max Range: 3.4126. Min Range: -3.4126

Max Act: 3.1455. Min Act: -0.1700

Data Index: 466143 (C4 (Web Text))

Max Activating Token Index: 157

Text #11

Max Range: 3.4126. Min Range: -3.4126

Max Act: 3.1140. Min Act: -0.1700

Data Index: 719043 (C4 (Web Text))

Max Activating Token Index: 675

Text #12

Max Range: 3.4126. Min Range: -3.4126

Max Act: 3.1297. Min Act: -0.1700

Data Index: 99242 (C4 (Web Text))

Max Activating Token Index: 726

Text #13

Max Range: 3.4126. Min Range: -3.4126

Max Act: 3.0035. Min Act: -0.1700

Data Index: 277466 (C4 (Web Text))

Max Activating Token Index: 311

Text #14

Max Range: 3.4126. Min Range: -3.4126

Max Act: 3.1140. Min Act: -0.1700

Data Index: 661491 (C4 (Web Text))

Max Activating Token Index: 53

Text #15

Max Range: 3.4126. Min Range: -3.4126

Max Act: 3.0982. Min Act: -0.1700

Data Index: 842307 (C4 (Web Text))

Max Activating Token Index: 762

Text #16

Max Range: 3.4126. Min Range: -3.4126

Max Act: 3.0824. Min Act: -0.1700

Data Index: 153816 (C4 (Web Text))

Max Activating Token Index: 655

Text #17

Max Range: 3.4126. Min Range: -3.4126

Max Act: 3.0667. Min Act: -0.1700

Data Index: 464622 (C4 (Web Text))

Max Activating Token Index: 672

Text #18

Max Range: 3.4126. Min Range: -3.4126

Max Act: 3.0193. Min Act: -0.1700

Data Index: 1531982 (Python Code)

Max Activating Token Index: 240

Text #19

Max Range: 3.4126. Min Range: -3.4126

Max Act: 3.0667. Min Act: -0.1700

Data Index: 290281 (C4 (Web Text))

Max Activating Token Index: 568