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

Dataset: Open Web Text

Neuron 760 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: 3.3565. Min Range: -3.3565

Max Act: 3.3565. Min Act: -0.1700

Data Index: 1679493 (Open Web Text)

Max Activating Token Index: 133

Text #1

Max Range: 3.3565. Min Range: -3.3565

Max Act: 3.3150. Min Act: -0.1700

Data Index: 330000 (Open Web Text)

Max Activating Token Index: 549

Text #2

Max Range: 3.3565. Min Range: -3.3565

Max Act: 3.2949. Min Act: -0.1700

Data Index: 8078577 (Open Web Text)

Max Activating Token Index: 310

Text #3

Max Range: 3.3565. Min Range: -3.3565

Max Act: 3.2634. Min Act: -0.1700

Data Index: 3694264 (Open Web Text)

Max Activating Token Index: 996

Text #4

Max Range: 3.3565. Min Range: -3.3565

Max Act: 3.2253. Min Act: -0.1700

Data Index: 7720343 (Open Web Text)

Max Activating Token Index: 607

Text #5

Max Range: 3.3565. Min Range: -3.3565

Max Act: 3.2266. Min Act: -0.1700

Data Index: 1786797 (Open Web Text)

Max Activating Token Index: 423

Text #6

Max Range: 3.3565. Min Range: -3.3565

Max Act: 3.2522. Min Act: -0.1700

Data Index: 4582803 (Open Web Text)

Max Activating Token Index: 218

Text #7

Max Range: 3.3565. Min Range: -3.3565

Max Act: 3.2168. Min Act: -0.1700

Data Index: 8588268 (Open Web Text)

Max Activating Token Index: 623

Text #8

Max Range: 3.3565. Min Range: -3.3565

Max Act: 3.2319. Min Act: -0.1700

Data Index: 7155777 (Open Web Text)

Max Activating Token Index: 534

Text #9

Max Range: 3.3565. Min Range: -3.3565

Max Act: 3.2083. Min Act: -0.1700

Data Index: 1819210 (Open Web Text)

Max Activating Token Index: 284

Text #10

Max Range: 3.3565. Min Range: -3.3565

Max Act: 3.2061. Min Act: -0.1700

Data Index: 4260255 (Open Web Text)

Max Activating Token Index: 695

Text #11

Max Range: 3.3565. Min Range: -3.3565

Max Act: 3.2168. Min Act: -0.1700

Data Index: 8018891 (Open Web Text)

Max Activating Token Index: 785

Text #12

Max Range: 3.3565. Min Range: -3.3565

Max Act: 3.2080. Min Act: -0.1700

Data Index: 7457176 (Open Web Text)

Max Activating Token Index: 440

Text #13

Max Range: 3.3565. Min Range: -3.3565

Max Act: 3.1964. Min Act: -0.1700

Data Index: 5593087 (Open Web Text)

Max Activating Token Index: 250

Text #14

Max Range: 3.3565. Min Range: -3.3565

Max Act: 3.1963. Min Act: -0.1700

Data Index: 6888210 (Open Web Text)

Max Activating Token Index: 550

Text #15

Max Range: 3.3565. Min Range: -3.3565

Max Act: 3.1776. Min Act: -0.1700

Data Index: 8184697 (Open Web Text)

Max Activating Token Index: 759

Text #16

Max Range: 3.3565. Min Range: -3.3565

Max Act: 3.1881. Min Act: -0.1700

Data Index: 3875776 (Open Web Text)

Max Activating Token Index: 887

Text #17

Max Range: 3.3565. Min Range: -3.3565

Max Act: 3.1834. Min Act: -0.1700

Data Index: 8175398 (Open Web Text)

Max Activating Token Index: 713

Text #18

Max Range: 3.3565. Min Range: -3.3565

Max Act: 3.1801. Min Act: -0.1700

Data Index: 4104163 (Open Web Text)

Max Activating Token Index: 411

Text #19

Max Range: 3.3565. Min Range: -3.3565

Max Act: 3.1789. Min Act: -0.1700

Data Index: 65858 (Open Web Text)

Max Activating Token Index: 1023