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

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

Neuron 1471 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6948. Min Range: -3.6948

Max Act: 3.6948. Min Act: -0.1700

Data Index: 1108208 (C4 (Web Text))

Max Activating Token Index: 185

Text #1

Max Range: 3.6948. Min Range: -3.6948

Max Act: 3.6948. Min Act: -0.1700

Data Index: 290615 (C4 (Web Text))

Max Activating Token Index: 611

Text #2

Max Range: 3.6948. Min Range: -3.6948

Max Act: 3.6948. Min Act: -0.1700

Data Index: 204608 (C4 (Web Text))

Max Activating Token Index: 880

Text #3

Max Range: 3.6948. Min Range: -3.6948

Max Act: 3.6322. Min Act: -0.1700

Data Index: 744740 (C4 (Web Text))

Max Activating Token Index: 634

Text #4

Max Range: 3.6948. Min Range: -3.6948

Max Act: 3.5696. Min Act: -0.1700

Data Index: 813478 (C4 (Web Text))

Max Activating Token Index: 801

Text #5

Max Range: 3.6948. Min Range: -3.6948

Max Act: 3.5383. Min Act: -0.1700

Data Index: 41688 (C4 (Web Text))

Max Activating Token Index: 881

Text #6

Max Range: 3.6948. Min Range: -3.6948

Max Act: 3.5226. Min Act: -0.1700

Data Index: 1334021 (C4 (Web Text))

Max Activating Token Index: 806

Text #7

Max Range: 3.6948. Min Range: -3.6948

Max Act: 3.4756. Min Act: -0.1700

Data Index: 1089007 (C4 (Web Text))

Max Activating Token Index: 741

Text #8

Max Range: 3.6948. Min Range: -3.6948

Max Act: 3.4756. Min Act: -0.1700

Data Index: 1161051 (C4 (Web Text))

Max Activating Token Index: 139

Text #9

Max Range: 3.6948. Min Range: -3.6948

Max Act: 3.4599. Min Act: -0.1700

Data Index: 1169444 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 3.6948. Min Range: -3.6948

Max Act: 3.4599. Min Act: -0.1700

Data Index: 583425 (C4 (Web Text))

Max Activating Token Index: 956

Text #11

Max Range: 3.6948. Min Range: -3.6948

Max Act: 3.4442. Min Act: -0.1700

Data Index: 522139 (C4 (Web Text))

Max Activating Token Index: 795

Text #12

Max Range: 3.6948. Min Range: -3.6948

Max Act: 3.4286. Min Act: -0.1700

Data Index: 1020422 (C4 (Web Text))

Max Activating Token Index: 516

Text #13

Max Range: 3.6948. Min Range: -3.6948

Max Act: 3.3972. Min Act: -0.1700

Data Index: 1114467 (C4 (Web Text))

Max Activating Token Index: 279

Text #14

Max Range: 3.6948. Min Range: -3.6948

Max Act: 3.4129. Min Act: -0.1700

Data Index: 1093691 (C4 (Web Text))

Max Activating Token Index: 107

Text #15

Max Range: 3.6948. Min Range: -3.6948

Max Act: 3.4129. Min Act: -0.1700

Data Index: 779489 (C4 (Web Text))

Max Activating Token Index: 606

Text #16

Max Range: 3.6948. Min Range: -3.6948

Max Act: 3.3972. Min Act: -0.1700

Data Index: 791110 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 3.6948. Min Range: -3.6948

Max Act: 3.3658. Min Act: -0.1700

Data Index: 619733 (C4 (Web Text))

Max Activating Token Index: 48

Text #18

Max Range: 3.6948. Min Range: -3.6948

Max Act: 3.3972. Min Act: -0.1700

Data Index: 1031089 (C4 (Web Text))

Max Activating Token Index: 884

Text #19

Max Range: 3.6948. Min Range: -3.6948

Max Act: 3.3972. Min Act: -0.1700

Data Index: 1159887 (C4 (Web Text))

Max Activating Token Index: 229