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

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

Neuron 1729 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.7936. Min Range: -8.7936

Max Act: 8.6686. Min Act: -0.1700

Data Index: 993378 (C4 (Web Text))

Max Activating Token Index: 91

Text #1

Max Range: 8.7936. Min Range: -8.7936

Max Act: 8.7311. Min Act: -0.1700

Data Index: 968371 (C4 (Web Text))

Max Activating Token Index: 160

Text #2

Max Range: 8.7936. Min Range: -8.7936

Max Act: 8.6998. Min Act: -0.1700

Data Index: 531902 (C4 (Web Text))

Max Activating Token Index: 95

Text #3

Max Range: 8.7936. Min Range: -8.7936

Max Act: 8.7936. Min Act: -0.1700

Data Index: 1334877 (C4 (Web Text))

Max Activating Token Index: 36

Text #4

Max Range: 8.7936. Min Range: -8.7936

Max Act: 8.5748. Min Act: -0.1700

Data Index: 384391 (C4 (Web Text))

Max Activating Token Index: 133

Text #5

Max Range: 8.7936. Min Range: -8.7936

Max Act: 8.6373. Min Act: -0.1700

Data Index: 787643 (C4 (Web Text))

Max Activating Token Index: 141

Text #6

Max Range: 8.7936. Min Range: -8.7936

Max Act: 8.5123. Min Act: -0.1700

Data Index: 1350879 (C4 (Web Text))

Max Activating Token Index: 620

Text #7

Max Range: 8.7936. Min Range: -8.7936

Max Act: 8.6061. Min Act: -0.1700

Data Index: 939023 (C4 (Web Text))

Max Activating Token Index: 139

Text #8

Max Range: 8.7936. Min Range: -8.7936

Max Act: 8.5123. Min Act: -0.1700

Data Index: 972685 (C4 (Web Text))

Max Activating Token Index: 169

Text #9

Max Range: 8.7936. Min Range: -8.7936

Max Act: 8.5123. Min Act: -0.1700

Data Index: 962406 (C4 (Web Text))

Max Activating Token Index: 138

Text #10

Max Range: 8.7936. Min Range: -8.7936

Max Act: 8.5123. Min Act: -0.1700

Data Index: 969159 (C4 (Web Text))

Max Activating Token Index: 121

Text #11

Max Range: 8.7936. Min Range: -8.7936

Max Act: 8.4498. Min Act: -0.1700

Data Index: 408596 (C4 (Web Text))

Max Activating Token Index: 927

Text #12

Max Range: 8.7936. Min Range: -8.7936

Max Act: 8.3873. Min Act: -0.1700

Data Index: 472652 (C4 (Web Text))

Max Activating Token Index: 88

Text #13

Max Range: 8.7936. Min Range: -8.7936

Max Act: 8.5436. Min Act: -0.1700

Data Index: 207461 (C4 (Web Text))

Max Activating Token Index: 844

Text #14

Max Range: 8.7936. Min Range: -8.7936

Max Act: 8.2623. Min Act: -0.1700

Data Index: 277344 (C4 (Web Text))

Max Activating Token Index: 291

Text #15

Max Range: 8.7936. Min Range: -8.7936

Max Act: 8.3873. Min Act: -0.1700

Data Index: 271652 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 8.7936. Min Range: -8.7936

Max Act: 8.4186. Min Act: -0.1700

Data Index: 1289685 (C4 (Web Text))

Max Activating Token Index: 44

Text #17

Max Range: 8.7936. Min Range: -8.7936

Max Act: 8.5123. Min Act: -0.1700

Data Index: 756898 (C4 (Web Text))

Max Activating Token Index: 255

Text #18

Max Range: 8.7936. Min Range: -8.7936

Max Act: 8.3248. Min Act: -0.1700

Data Index: 1072049 (C4 (Web Text))

Max Activating Token Index: 236

Text #19

Max Range: 8.7936. Min Range: -8.7936

Max Act: 8.4186. Min Act: -0.1700

Data Index: 435126 (C4 (Web Text))

Max Activating Token Index: 249