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

Dataset: Open Web Text

Neuron 1106 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: 4.4016. Min Range: -4.4016

Max Act: 4.4016. Min Act: -0.1700

Data Index: 5920624 (Open Web Text)

Max Activating Token Index: 173

Text #1

Max Range: 4.4016. Min Range: -4.4016

Max Act: 4.3686. Min Act: -0.1700

Data Index: 2215480 (Open Web Text)

Max Activating Token Index: 256

Text #2

Max Range: 4.4016. Min Range: -4.4016

Max Act: 4.2986. Min Act: -0.1700

Data Index: 2469836 (Open Web Text)

Max Activating Token Index: 171

Text #3

Max Range: 4.4016. Min Range: -4.4016

Max Act: 4.3012. Min Act: -0.1700

Data Index: 3515757 (Open Web Text)

Max Activating Token Index: 410

Text #4

Max Range: 4.4016. Min Range: -4.4016

Max Act: 4.3342. Min Act: -0.1700

Data Index: 8428116 (Open Web Text)

Max Activating Token Index: 129

Text #5

Max Range: 4.4016. Min Range: -4.4016

Max Act: 4.3021. Min Act: -0.1700

Data Index: 7732682 (Open Web Text)

Max Activating Token Index: 39

Text #6

Max Range: 4.4016. Min Range: -4.4016

Max Act: 4.2631. Min Act: -0.1700

Data Index: 317832 (Open Web Text)

Max Activating Token Index: 433

Text #7

Max Range: 4.4016. Min Range: -4.4016

Max Act: 4.2141. Min Act: -0.1700

Data Index: 6773858 (Open Web Text)

Max Activating Token Index: 1000

Text #8

Max Range: 4.4016. Min Range: -4.4016

Max Act: 4.2043. Min Act: -0.1700

Data Index: 3176334 (Open Web Text)

Max Activating Token Index: 360

Text #9

Max Range: 4.4016. Min Range: -4.4016

Max Act: 4.1731. Min Act: -0.1700

Data Index: 1066216 (Open Web Text)

Max Activating Token Index: 407

Text #10

Max Range: 4.4016. Min Range: -4.4016

Max Act: 4.1903. Min Act: -0.1700

Data Index: 296184 (Open Web Text)

Max Activating Token Index: 445

Text #11

Max Range: 4.4016. Min Range: -4.4016

Max Act: 4.1482. Min Act: -0.1700

Data Index: 4316150 (Open Web Text)

Max Activating Token Index: 694

Text #12

Max Range: 4.4016. Min Range: -4.4016

Max Act: 4.1621. Min Act: -0.1700

Data Index: 3415967 (Open Web Text)

Max Activating Token Index: 398

Text #13

Max Range: 4.4016. Min Range: -4.4016

Max Act: 4.1603. Min Act: -0.1700

Data Index: 3794684 (Open Web Text)

Max Activating Token Index: 258

Text #14

Max Range: 4.4016. Min Range: -4.4016

Max Act: 4.1261. Min Act: -0.1700

Data Index: 5177012 (Open Web Text)

Max Activating Token Index: 124

Text #15

Max Range: 4.4016. Min Range: -4.4016

Max Act: 4.1443. Min Act: -0.1700

Data Index: 5741879 (Open Web Text)

Max Activating Token Index: 669

Text #16

Max Range: 4.4016. Min Range: -4.4016

Max Act: 4.1209. Min Act: -0.1700

Data Index: 185445 (Open Web Text)

Max Activating Token Index: 563

Text #17

Max Range: 4.4016. Min Range: -4.4016

Max Act: 4.1162. Min Act: -0.1700

Data Index: 5050381 (Open Web Text)

Max Activating Token Index: 145

Text #18

Max Range: 4.4016. Min Range: -4.4016

Max Act: 4.1412. Min Act: -0.1700

Data Index: 3436672 (Open Web Text)

Max Activating Token Index: 417

Text #19

Max Range: 4.4016. Min Range: -4.4016

Max Act: 4.1172. Min Act: -0.1700

Data Index: 5893997 (Open Web Text)

Max Activating Token Index: 140