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

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

Neuron 120 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: 4.0774. Min Range: -4.0774

Max Act: 4.0774. Min Act: -0.1700

Data Index: 669264 (C4 (Web Text))

Max Activating Token Index: 401

Text #1

Max Range: 4.0774. Min Range: -4.0774

Max Act: 3.9210. Min Act: -0.1700

Data Index: 469582 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 4.0774. Min Range: -4.0774

Max Act: 3.9210. Min Act: -0.1700

Data Index: 674258 (C4 (Web Text))

Max Activating Token Index: 534

Text #3

Max Range: 4.0774. Min Range: -4.0774

Max Act: 3.8898. Min Act: -0.1700

Data Index: 413199 (C4 (Web Text))

Max Activating Token Index: 810

Text #4

Max Range: 4.0774. Min Range: -4.0774

Max Act: 3.8585. Min Act: -0.1700

Data Index: 787326 (C4 (Web Text))

Max Activating Token Index: 76

Text #5

Max Range: 4.0774. Min Range: -4.0774

Max Act: 3.8585. Min Act: -0.1700

Data Index: 524756 (C4 (Web Text))

Max Activating Token Index: 301

Text #6

Max Range: 4.0774. Min Range: -4.0774

Max Act: 3.8585. Min Act: -0.1700

Data Index: 1008747 (C4 (Web Text))

Max Activating Token Index: 63

Text #7

Max Range: 4.0774. Min Range: -4.0774

Max Act: 3.8585. Min Act: -0.1700

Data Index: 1167664 (C4 (Web Text))

Max Activating Token Index: 93

Text #8

Max Range: 4.0774. Min Range: -4.0774

Max Act: 3.8585. Min Act: -0.1700

Data Index: 1207158 (C4 (Web Text))

Max Activating Token Index: 162

Text #9

Max Range: 4.0774. Min Range: -4.0774

Max Act: 3.8272. Min Act: -0.1700

Data Index: 190795 (C4 (Web Text))

Max Activating Token Index: 698

Text #10

Max Range: 4.0774. Min Range: -4.0774

Max Act: 3.8272. Min Act: -0.1700

Data Index: 540113 (C4 (Web Text))

Max Activating Token Index: 632

Text #11

Max Range: 4.0774. Min Range: -4.0774

Max Act: 3.8272. Min Act: -0.1700

Data Index: 1044280 (C4 (Web Text))

Max Activating Token Index: 93

Text #12

Max Range: 4.0774. Min Range: -4.0774

Max Act: 3.8272. Min Act: -0.1700

Data Index: 182376 (C4 (Web Text))

Max Activating Token Index: 664

Text #13

Max Range: 4.0774. Min Range: -4.0774

Max Act: 3.8272. Min Act: -0.1700

Data Index: 56583 (C4 (Web Text))

Max Activating Token Index: 177

Text #14

Max Range: 4.0774. Min Range: -4.0774

Max Act: 3.8272. Min Act: -0.1700

Data Index: 496142 (C4 (Web Text))

Max Activating Token Index: 210

Text #15

Max Range: 4.0774. Min Range: -4.0774

Max Act: 3.8272. Min Act: -0.1700

Data Index: 812759 (C4 (Web Text))

Max Activating Token Index: 208

Text #16

Max Range: 4.0774. Min Range: -4.0774

Max Act: 3.7959. Min Act: -0.1700

Data Index: 451201 (C4 (Web Text))

Max Activating Token Index: 105

Text #17

Max Range: 4.0774. Min Range: -4.0774

Max Act: 3.7959. Min Act: -0.1700

Data Index: 463632 (C4 (Web Text))

Max Activating Token Index: 467

Text #18

Max Range: 4.0774. Min Range: -4.0774

Max Act: 3.7959. Min Act: -0.1700

Data Index: 212143 (C4 (Web Text))

Max Activating Token Index: 593

Text #19

Max Range: 4.0774. Min Range: -4.0774

Max Act: 3.7959. Min Act: -0.1700

Data Index: 762656 (C4 (Web Text))

Max Activating Token Index: 112