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

Dataset: Open Web Text

Neuron 126 in Layer 4

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: 4.2070. Min Range: -4.2070

Max Act: 4.2017. Min Act: -0.1700

Data Index: 3664828 (Open Web Text)

Max Activating Token Index: 507

Text #1

Max Range: 4.2070. Min Range: -4.2070

Max Act: 4.2070. Min Act: -0.1699

Data Index: 2321447 (Open Web Text)

Max Activating Token Index: 341

Text #2

Max Range: 4.2070. Min Range: -4.2070

Max Act: 4.1972. Min Act: -0.1700

Data Index: 7404162 (Open Web Text)

Max Activating Token Index: 245

Text #3

Max Range: 4.2070. Min Range: -4.2070

Max Act: 4.1607. Min Act: -0.1700

Data Index: 7861258 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 4.2070. Min Range: -4.2070

Max Act: 4.1325. Min Act: -0.1698

Data Index: 6382001 (Open Web Text)

Max Activating Token Index: 356

Text #5

Max Range: 4.2070. Min Range: -4.2070

Max Act: 4.1197. Min Act: -0.1700

Data Index: 1000806 (Open Web Text)

Max Activating Token Index: 395

Text #6

Max Range: 4.2070. Min Range: -4.2070

Max Act: 4.1521. Min Act: -0.1700

Data Index: 7666848 (Open Web Text)

Max Activating Token Index: 165

Text #7

Max Range: 4.2070. Min Range: -4.2070

Max Act: 4.1643. Min Act: -0.1698

Data Index: 99868 (Open Web Text)

Max Activating Token Index: 80

Text #8

Max Range: 4.2070. Min Range: -4.2070

Max Act: 4.1395. Min Act: -0.1697

Data Index: 6147387 (Open Web Text)

Max Activating Token Index: 600

Text #9

Max Range: 4.2070. Min Range: -4.2070

Max Act: 4.1473. Min Act: -0.1699

Data Index: 6326937 (Open Web Text)

Max Activating Token Index: 943

Text #10

Max Range: 4.2070. Min Range: -4.2070

Max Act: 4.1144. Min Act: -0.1700

Data Index: 2330444 (Open Web Text)

Max Activating Token Index: 294

Text #11

Max Range: 4.2070. Min Range: -4.2070

Max Act: 4.0862. Min Act: -0.1700

Data Index: 2041766 (Open Web Text)

Max Activating Token Index: 632

Text #12

Max Range: 4.2070. Min Range: -4.2070

Max Act: 4.0990. Min Act: -0.1700

Data Index: 5642612 (Open Web Text)

Max Activating Token Index: 26

Text #13

Max Range: 4.2070. Min Range: -4.2070

Max Act: 4.1010. Min Act: -0.1700

Data Index: 807530 (Open Web Text)

Max Activating Token Index: 12

Text #14

Max Range: 4.2070. Min Range: -4.2070

Max Act: 4.0595. Min Act: -0.1700

Data Index: 4716500 (Open Web Text)

Max Activating Token Index: 520

Text #15

Max Range: 4.2070. Min Range: -4.2070

Max Act: 4.0439. Min Act: -0.1700

Data Index: 824696 (Open Web Text)

Max Activating Token Index: 21

Text #16

Max Range: 4.2070. Min Range: -4.2070

Max Act: 4.0515. Min Act: -0.1698

Data Index: 5654237 (Open Web Text)

Max Activating Token Index: 202

Text #17

Max Range: 4.2070. Min Range: -4.2070

Max Act: 4.0910. Min Act: -0.1700

Data Index: 2803014 (Open Web Text)

Max Activating Token Index: 437

Text #18

Max Range: 4.2070. Min Range: -4.2070

Max Act: 4.0601. Min Act: -0.1700

Data Index: 4725250 (Open Web Text)

Max Activating Token Index: 872

Text #19

Max Range: 4.2070. Min Range: -4.2070

Max Act: 4.0232. Min Act: -0.1697

Data Index: 4520338 (Open Web Text)

Max Activating Token Index: 544