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

Dataset: Open Web Text

Neuron 2077 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: 4.2417. Min Range: -4.2417

Max Act: 4.2352. Min Act: -0.1700

Data Index: 8687147 (Open Web Text)

Max Activating Token Index: 303

Text #1

Max Range: 4.2417. Min Range: -4.2417

Max Act: 4.1796. Min Act: -0.1700

Data Index: 8714788 (Open Web Text)

Max Activating Token Index: 176

Text #2

Max Range: 4.2417. Min Range: -4.2417

Max Act: 4.1732. Min Act: -0.1700

Data Index: 1277192 (Open Web Text)

Max Activating Token Index: 200

Text #3

Max Range: 4.2417. Min Range: -4.2417

Max Act: 4.2417. Min Act: -0.1700

Data Index: 6815901 (Open Web Text)

Max Activating Token Index: 478

Text #4

Max Range: 4.2417. Min Range: -4.2417

Max Act: 4.1638. Min Act: -0.1700

Data Index: 4095864 (Open Web Text)

Max Activating Token Index: 119

Text #5

Max Range: 4.2417. Min Range: -4.2417

Max Act: 4.1508. Min Act: -0.1700

Data Index: 323904 (Open Web Text)

Max Activating Token Index: 70

Text #6

Max Range: 4.2417. Min Range: -4.2417

Max Act: 4.1351. Min Act: -0.1700

Data Index: 4986598 (Open Web Text)

Max Activating Token Index: 128

Text #7

Max Range: 4.2417. Min Range: -4.2417

Max Act: 4.1058. Min Act: -0.1700

Data Index: 8150879 (Open Web Text)

Max Activating Token Index: 801

Text #8

Max Range: 4.2417. Min Range: -4.2417

Max Act: 4.1137. Min Act: -0.1700

Data Index: 791817 (Open Web Text)

Max Activating Token Index: 574

Text #9

Max Range: 4.2417. Min Range: -4.2417

Max Act: 4.0960. Min Act: -0.1700

Data Index: 4008167 (Open Web Text)

Max Activating Token Index: 194

Text #10

Max Range: 4.2417. Min Range: -4.2417

Max Act: 4.1041. Min Act: -0.1700

Data Index: 8360623 (Open Web Text)

Max Activating Token Index: 346

Text #11

Max Range: 4.2417. Min Range: -4.2417

Max Act: 4.0909. Min Act: -0.1700

Data Index: 917476 (Open Web Text)

Max Activating Token Index: 313

Text #12

Max Range: 4.2417. Min Range: -4.2417

Max Act: 4.0956. Min Act: -0.1700

Data Index: 8210260 (Open Web Text)

Max Activating Token Index: 320

Text #13

Max Range: 4.2417. Min Range: -4.2417

Max Act: 4.0873. Min Act: -0.1700

Data Index: 6096616 (Open Web Text)

Max Activating Token Index: 444

Text #14

Max Range: 4.2417. Min Range: -4.2417

Max Act: 4.1016. Min Act: -0.1700

Data Index: 804818 (Open Web Text)

Max Activating Token Index: 248

Text #15

Max Range: 4.2417. Min Range: -4.2417

Max Act: 4.0895. Min Act: -0.1700

Data Index: 7858050 (Open Web Text)

Max Activating Token Index: 470

Text #16

Max Range: 4.2417. Min Range: -4.2417

Max Act: 4.0777. Min Act: -0.1700

Data Index: 7775825 (Open Web Text)

Max Activating Token Index: 261

Text #17

Max Range: 4.2417. Min Range: -4.2417

Max Act: 4.0713. Min Act: -0.1700

Data Index: 3310418 (Open Web Text)

Max Activating Token Index: 202

Text #18

Max Range: 4.2417. Min Range: -4.2417

Max Act: 4.0567. Min Act: -0.1700

Data Index: 8137344 (Open Web Text)

Max Activating Token Index: 853

Text #19

Max Range: 4.2417. Min Range: -4.2417

Max Act: 4.0954. Min Act: -0.1700

Data Index: 3669678 (Open Web Text)

Max Activating Token Index: 938