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

Dataset: Open Web Text

Neuron 1702 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: 2.3559. Min Range: -2.3559

Max Act: 2.3559. Min Act: -0.1700

Data Index: 1628375 (Open Web Text)

Max Activating Token Index: 62

Text #1

Max Range: 2.3559. Min Range: -2.3559

Max Act: 2.3046. Min Act: -0.1700

Data Index: 6489402 (Open Web Text)

Max Activating Token Index: 61

Text #2

Max Range: 2.3559. Min Range: -2.3559

Max Act: 2.2894. Min Act: -0.1700

Data Index: 3772817 (Open Web Text)

Max Activating Token Index: 690

Text #3

Max Range: 2.3559. Min Range: -2.3559

Max Act: 2.2552. Min Act: -0.1700

Data Index: 1885341 (Open Web Text)

Max Activating Token Index: 597

Text #4

Max Range: 2.3559. Min Range: -2.3559

Max Act: 2.2291. Min Act: -0.1699

Data Index: 3342525 (Open Web Text)

Max Activating Token Index: 678

Text #5

Max Range: 2.3559. Min Range: -2.3559

Max Act: 2.2527. Min Act: -0.1700

Data Index: 3131914 (Open Web Text)

Max Activating Token Index: 551

Text #6

Max Range: 2.3559. Min Range: -2.3559

Max Act: 2.2110. Min Act: -0.1700

Data Index: 394833 (Open Web Text)

Max Activating Token Index: 671

Text #7

Max Range: 2.3559. Min Range: -2.3559

Max Act: 2.2152. Min Act: -0.1698

Data Index: 5532371 (Open Web Text)

Max Activating Token Index: 853

Text #8

Max Range: 2.3559. Min Range: -2.3559

Max Act: 2.2068. Min Act: -0.1696

Data Index: 4440365 (Open Web Text)

Max Activating Token Index: 627

Text #9

Max Range: 2.3559. Min Range: -2.3559

Max Act: 2.2016. Min Act: -0.1700

Data Index: 7886524 (Open Web Text)

Max Activating Token Index: 260

Text #10

Max Range: 2.3559. Min Range: -2.3559

Max Act: 2.1940. Min Act: -0.1700

Data Index: 5436087 (Open Web Text)

Max Activating Token Index: 327

Text #11

Max Range: 2.3559. Min Range: -2.3559

Max Act: 2.2055. Min Act: -0.1700

Data Index: 7523958 (Open Web Text)

Max Activating Token Index: 490

Text #12

Max Range: 2.3559. Min Range: -2.3559

Max Act: 2.2087. Min Act: -0.1700

Data Index: 5070821 (Open Web Text)

Max Activating Token Index: 643

Text #13

Max Range: 2.3559. Min Range: -2.3559

Max Act: 2.2093. Min Act: -0.1700

Data Index: 917034 (Open Web Text)

Max Activating Token Index: 371

Text #14

Max Range: 2.3559. Min Range: -2.3559

Max Act: 2.1820. Min Act: -0.1700

Data Index: 2672402 (Open Web Text)

Max Activating Token Index: 265

Text #15

Max Range: 2.3559. Min Range: -2.3559

Max Act: 2.1763. Min Act: -0.1700

Data Index: 3017278 (Open Web Text)

Max Activating Token Index: 502

Text #16

Max Range: 2.3559. Min Range: -2.3559

Max Act: 2.1863. Min Act: -0.1700

Data Index: 974924 (Open Web Text)

Max Activating Token Index: 719

Text #17

Max Range: 2.3559. Min Range: -2.3559

Max Act: 2.1846. Min Act: -0.1700

Data Index: 2110368 (Open Web Text)

Max Activating Token Index: 250

Text #18

Max Range: 2.3559. Min Range: -2.3559

Max Act: 2.1842. Min Act: -0.1700

Data Index: 2180605 (Open Web Text)

Max Activating Token Index: 492

Text #19

Max Range: 2.3559. Min Range: -2.3559

Max Act: 2.1900. Min Act: -0.1700

Data Index: 5607122 (Open Web Text)

Max Activating Token Index: 537