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

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

Neuron 1739 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5839. Min Range: -3.5839

Max Act: 3.5839. Min Act: -0.1700

Data Index: 448217 (C4 (Web Text))

Max Activating Token Index: 102

Text #1

Max Range: 3.5839. Min Range: -3.5839

Max Act: 3.5526. Min Act: -0.1700

Data Index: 384228 (C4 (Web Text))

Max Activating Token Index: 97

Text #2

Max Range: 3.5839. Min Range: -3.5839

Max Act: 3.5369. Min Act: -0.1700

Data Index: 672659 (C4 (Web Text))

Max Activating Token Index: 90

Text #3

Max Range: 3.5839. Min Range: -3.5839

Max Act: 3.5213. Min Act: -0.1700

Data Index: 875793 (C4 (Web Text))

Max Activating Token Index: 99

Text #4

Max Range: 3.5839. Min Range: -3.5839

Max Act: 3.5056. Min Act: -0.1700

Data Index: 1134798 (C4 (Web Text))

Max Activating Token Index: 87

Text #5

Max Range: 3.5839. Min Range: -3.5839

Max Act: 3.5213. Min Act: -0.1700

Data Index: 1219233 (C4 (Web Text))

Max Activating Token Index: 99

Text #6

Max Range: 3.5839. Min Range: -3.5839

Max Act: 3.4899. Min Act: -0.1700

Data Index: 599559 (C4 (Web Text))

Max Activating Token Index: 77

Text #7

Max Range: 3.5839. Min Range: -3.5839

Max Act: 3.4743. Min Act: -0.1700

Data Index: 1139436 (C4 (Web Text))

Max Activating Token Index: 99

Text #8

Max Range: 3.5839. Min Range: -3.5839

Max Act: 3.4899. Min Act: -0.1700

Data Index: 490711 (C4 (Web Text))

Max Activating Token Index: 87

Text #9

Max Range: 3.5839. Min Range: -3.5839

Max Act: 3.4743. Min Act: -0.1700

Data Index: 645295 (C4 (Web Text))

Max Activating Token Index: 131

Text #10

Max Range: 3.5839. Min Range: -3.5839

Max Act: 3.5056. Min Act: -0.1700

Data Index: 844942 (C4 (Web Text))

Max Activating Token Index: 88

Text #11

Max Range: 3.5839. Min Range: -3.5839

Max Act: 3.4899. Min Act: -0.1700

Data Index: 1243132 (C4 (Web Text))

Max Activating Token Index: 94

Text #12

Max Range: 3.5839. Min Range: -3.5839

Max Act: 3.4899. Min Act: -0.1700

Data Index: 1097498 (C4 (Web Text))

Max Activating Token Index: 109

Text #13

Max Range: 3.5839. Min Range: -3.5839

Max Act: 3.4743. Min Act: -0.1700

Data Index: 1330773 (C4 (Web Text))

Max Activating Token Index: 94

Text #14

Max Range: 3.5839. Min Range: -3.5839

Max Act: 3.4743. Min Act: -0.1700

Data Index: 938420 (C4 (Web Text))

Max Activating Token Index: 68

Text #15

Max Range: 3.5839. Min Range: -3.5839

Max Act: 3.4743. Min Act: -0.1700

Data Index: 995719 (C4 (Web Text))

Max Activating Token Index: 98

Text #16

Max Range: 3.5839. Min Range: -3.5839

Max Act: 3.4743. Min Act: -0.1700

Data Index: 1004507 (C4 (Web Text))

Max Activating Token Index: 115

Text #17

Max Range: 3.5839. Min Range: -3.5839

Max Act: 3.4743. Min Act: -0.1700

Data Index: 1007917 (C4 (Web Text))

Max Activating Token Index: 93

Text #18

Max Range: 3.5839. Min Range: -3.5839

Max Act: 3.4743. Min Act: -0.1700

Data Index: 1091988 (C4 (Web Text))

Max Activating Token Index: 102

Text #19

Max Range: 3.5839. Min Range: -3.5839

Max Act: 3.4743. Min Act: -0.1700

Data Index: 296476 (C4 (Web Text))

Max Activating Token Index: 98