Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2301 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 1.7868. Min Range: -1.7868

Max Act: 1.7868. Min Act: -0.1700

Data Index: 6699070 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 1.7868. Min Range: -1.7868

Max Act: 1.7699. Min Act: -0.1700

Data Index: 7457438 (Open Web Text)

Max Activating Token Index: 417

Text #2

Max Range: 1.7868. Min Range: -1.7868

Max Act: 1.7179. Min Act: -0.1700

Data Index: 6694610 (Open Web Text)

Max Activating Token Index: 47

Text #3

Max Range: 1.7868. Min Range: -1.7868

Max Act: 1.7193. Min Act: -0.1700

Data Index: 4258037 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 1.7868. Min Range: -1.7868

Max Act: 1.7165. Min Act: -0.1700

Data Index: 7028138 (Open Web Text)

Max Activating Token Index: 791

Text #5

Max Range: 1.7868. Min Range: -1.7868

Max Act: 1.7079. Min Act: -0.1700

Data Index: 8531460 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 1.7868. Min Range: -1.7868

Max Act: 1.6992. Min Act: -0.1700

Data Index: 3856726 (Open Web Text)

Max Activating Token Index: 553

Text #7

Max Range: 1.7868. Min Range: -1.7868

Max Act: 1.7149. Min Act: -0.1700

Data Index: 3523125 (Open Web Text)

Max Activating Token Index: 11

Text #8

Max Range: 1.7868. Min Range: -1.7868

Max Act: 1.6928. Min Act: -0.1700

Data Index: 5352758 (Open Web Text)

Max Activating Token Index: 541

Text #9

Max Range: 1.7868. Min Range: -1.7868

Max Act: 1.6948. Min Act: -0.1700

Data Index: 2356149 (Open Web Text)

Max Activating Token Index: 14

Text #10

Max Range: 1.7868. Min Range: -1.7868

Max Act: 1.7038. Min Act: -0.1700

Data Index: 2445688 (Open Web Text)

Max Activating Token Index: 115

Text #11

Max Range: 1.7868. Min Range: -1.7868

Max Act: 1.6789. Min Act: -0.1700

Data Index: 373123 (Open Web Text)

Max Activating Token Index: 767

Text #12

Max Range: 1.7868. Min Range: -1.7868

Max Act: 1.6762. Min Act: -0.1700

Data Index: 3047717 (Open Web Text)

Max Activating Token Index: 511

Text #13

Max Range: 1.7868. Min Range: -1.7868

Max Act: 1.6786. Min Act: -0.1699

Data Index: 3233779 (Open Web Text)

Max Activating Token Index: 491

Text #14

Max Range: 1.7868. Min Range: -1.7868

Max Act: 1.6723. Min Act: -0.1700

Data Index: 1387250 (Open Web Text)

Max Activating Token Index: 217

Text #15

Max Range: 1.7868. Min Range: -1.7868

Max Act: 1.6727. Min Act: -0.1700

Data Index: 1445809 (Open Web Text)

Max Activating Token Index: 911

Text #16

Max Range: 1.7868. Min Range: -1.7868

Max Act: 1.6722. Min Act: -0.1700

Data Index: 2521231 (Open Web Text)

Max Activating Token Index: 483

Text #17

Max Range: 1.7868. Min Range: -1.7868

Max Act: 1.6670. Min Act: -0.1700

Data Index: 6117759 (Open Web Text)

Max Activating Token Index: 988

Text #18

Max Range: 1.7868. Min Range: -1.7868

Max Act: 1.6646. Min Act: -0.1698

Data Index: 296339 (Open Web Text)

Max Activating Token Index: 979

Text #19

Max Range: 1.7868. Min Range: -1.7868

Max Act: 1.6684. Min Act: -0.1699

Data Index: 2296689 (Open Web Text)

Max Activating Token Index: 800