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

Dataset: Open Web Text

Neuron 1045 in Layer 5

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: 5.6796. Min Range: -5.6796

Max Act: 5.6796. Min Act: -0.1700

Data Index: 4550310 (Open Web Text)

Max Activating Token Index: 1011

Text #1

Max Range: 5.6796. Min Range: -5.6796

Max Act: 5.4656. Min Act: -0.1700

Data Index: 6704921 (Open Web Text)

Max Activating Token Index: 614

Text #2

Max Range: 5.6796. Min Range: -5.6796

Max Act: 5.4339. Min Act: -0.1700

Data Index: 8027785 (Open Web Text)

Max Activating Token Index: 828

Text #3

Max Range: 5.6796. Min Range: -5.6796

Max Act: 5.3604. Min Act: -0.1700

Data Index: 6501181 (Open Web Text)

Max Activating Token Index: 1005

Text #4

Max Range: 5.6796. Min Range: -5.6796

Max Act: 5.3991. Min Act: -0.1700

Data Index: 2854291 (Open Web Text)

Max Activating Token Index: 462

Text #5

Max Range: 5.6796. Min Range: -5.6796

Max Act: 5.3512. Min Act: -0.1700

Data Index: 8665592 (Open Web Text)

Max Activating Token Index: 1000

Text #6

Max Range: 5.6796. Min Range: -5.6796

Max Act: 5.3076. Min Act: -0.1700

Data Index: 1923331 (Open Web Text)

Max Activating Token Index: 513

Text #7

Max Range: 5.6796. Min Range: -5.6796

Max Act: 5.2679. Min Act: -0.1700

Data Index: 5716764 (Open Web Text)

Max Activating Token Index: 737

Text #8

Max Range: 5.6796. Min Range: -5.6796

Max Act: 5.2747. Min Act: -0.1700

Data Index: 8770604 (Open Web Text)

Max Activating Token Index: 930

Text #9

Max Range: 5.6796. Min Range: -5.6796

Max Act: 5.2581. Min Act: -0.1700

Data Index: 7538318 (Open Web Text)

Max Activating Token Index: 250

Text #10

Max Range: 5.6796. Min Range: -5.6796

Max Act: 5.2639. Min Act: -0.1700

Data Index: 2163115 (Open Web Text)

Max Activating Token Index: 195

Text #11

Max Range: 5.6796. Min Range: -5.6796

Max Act: 5.2060. Min Act: -0.1700

Data Index: 3038860 (Open Web Text)

Max Activating Token Index: 521

Text #12

Max Range: 5.6796. Min Range: -5.6796

Max Act: 5.2487. Min Act: -0.1700

Data Index: 4520976 (Open Web Text)

Max Activating Token Index: 172

Text #13

Max Range: 5.6796. Min Range: -5.6796

Max Act: 5.2896. Min Act: -0.1700

Data Index: 1771154 (Open Web Text)

Max Activating Token Index: 648

Text #14

Max Range: 5.6796. Min Range: -5.6796

Max Act: 5.1909. Min Act: -0.1700

Data Index: 8469232 (Open Web Text)

Max Activating Token Index: 576

Text #15

Max Range: 5.6796. Min Range: -5.6796

Max Act: 5.1837. Min Act: -0.1700

Data Index: 5135171 (Open Web Text)

Max Activating Token Index: 772

Text #16

Max Range: 5.6796. Min Range: -5.6796

Max Act: 5.1680. Min Act: -0.1700

Data Index: 7778734 (Open Web Text)

Max Activating Token Index: 315

Text #17

Max Range: 5.6796. Min Range: -5.6796

Max Act: 5.1887. Min Act: -0.1700

Data Index: 7976228 (Open Web Text)

Max Activating Token Index: 659

Text #18

Max Range: 5.6796. Min Range: -5.6796

Max Act: 5.1850. Min Act: -0.1700

Data Index: 7031016 (Open Web Text)

Max Activating Token Index: 786

Text #19

Max Range: 5.6796. Min Range: -5.6796

Max Act: 5.1769. Min Act: -0.1700

Data Index: 5058367 (Open Web Text)

Max Activating Token Index: 791