Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1907 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.1328. Min Range: -4.1328

Max Act: 4.1236. Min Act: -0.1700

Data Index: 585068 (C4 (Web Text))

Max Activating Token Index: 405

Text #1

Max Range: 4.1328. Min Range: -4.1328

Max Act: 4.1328. Min Act: -0.1700

Data Index: 595118 (C4 (Web Text))

Max Activating Token Index: 974

Text #2

Max Range: 4.1328. Min Range: -4.1328

Max Act: 4.0239. Min Act: -0.1700

Data Index: 912671 (C4 (Web Text))

Max Activating Token Index: 997

Text #3

Max Range: 4.1328. Min Range: -4.1328

Max Act: 3.9828. Min Act: -0.1700

Data Index: 688795 (C4 (Web Text))

Max Activating Token Index: 696

Text #4

Max Range: 4.1328. Min Range: -4.1328

Max Act: 3.9597. Min Act: -0.1700

Data Index: 885428 (C4 (Web Text))

Max Activating Token Index: 173

Text #5

Max Range: 4.1328. Min Range: -4.1328

Max Act: 3.9236. Min Act: -0.1700

Data Index: 552828 (C4 (Web Text))

Max Activating Token Index: 899

Text #6

Max Range: 4.1328. Min Range: -4.1328

Max Act: 3.9157. Min Act: -0.1700

Data Index: 1254666 (C4 (Web Text))

Max Activating Token Index: 573

Text #7

Max Range: 4.1328. Min Range: -4.1328

Max Act: 3.9463. Min Act: -0.1700

Data Index: 89869 (C4 (Web Text))

Max Activating Token Index: 517

Text #8

Max Range: 4.1328. Min Range: -4.1328

Max Act: 3.9451. Min Act: -0.1700

Data Index: 926703 (C4 (Web Text))

Max Activating Token Index: 167

Text #9

Max Range: 4.1328. Min Range: -4.1328

Max Act: 3.9177. Min Act: -0.1700

Data Index: 84724 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 4.1328. Min Range: -4.1328

Max Act: 3.9107. Min Act: -0.1700

Data Index: 858525 (C4 (Web Text))

Max Activating Token Index: 604

Text #11

Max Range: 4.1328. Min Range: -4.1328

Max Act: 3.9239. Min Act: -0.1700

Data Index: 609912 (C4 (Web Text))

Max Activating Token Index: 63

Text #12

Max Range: 4.1328. Min Range: -4.1328

Max Act: 3.8951. Min Act: -0.1700

Data Index: 259793 (C4 (Web Text))

Max Activating Token Index: 347

Text #13

Max Range: 4.1328. Min Range: -4.1328

Max Act: 3.8918. Min Act: -0.1700

Data Index: 753993 (C4 (Web Text))

Max Activating Token Index: 633

Text #14

Max Range: 4.1328. Min Range: -4.1328

Max Act: 3.8954. Min Act: -0.1700

Data Index: 718955 (C4 (Web Text))

Max Activating Token Index: 170

Text #15

Max Range: 4.1328. Min Range: -4.1328

Max Act: 3.8885. Min Act: -0.1700

Data Index: 1157644 (C4 (Web Text))

Max Activating Token Index: 136

Text #16

Max Range: 4.1328. Min Range: -4.1328

Max Act: 3.8759. Min Act: -0.1700

Data Index: 805446 (C4 (Web Text))

Max Activating Token Index: 160

Text #17

Max Range: 4.1328. Min Range: -4.1328

Max Act: 3.9097. Min Act: -0.1700

Data Index: 1150886 (C4 (Web Text))

Max Activating Token Index: 499

Text #18

Max Range: 4.1328. Min Range: -4.1328

Max Act: 3.9046. Min Act: -0.1700

Data Index: 937734 (C4 (Web Text))

Max Activating Token Index: 771

Text #19

Max Range: 4.1328. Min Range: -4.1328

Max Act: 3.8866. Min Act: -0.1700

Data Index: 1333201 (C4 (Web Text))

Max Activating Token Index: 433