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

Dataset: Open Web Text

Neuron 981 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: 1.6931. Min Range: -1.6931

Max Act: 1.6931. Min Act: -0.1700

Data Index: 3306453 (Open Web Text)

Max Activating Token Index: 113

Text #1

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.6822. Min Act: -0.1698

Data Index: 2809171 (Open Web Text)

Max Activating Token Index: 208

Text #2

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.6412. Min Act: -0.1690

Data Index: 3526442 (Open Web Text)

Max Activating Token Index: 526

Text #3

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.6368. Min Act: -0.1700

Data Index: 1467607 (Open Web Text)

Max Activating Token Index: 744

Text #4

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.6446. Min Act: -0.1699

Data Index: 7384781 (Open Web Text)

Max Activating Token Index: 511

Text #5

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.6352. Min Act: -0.1700

Data Index: 5177461 (Open Web Text)

Max Activating Token Index: 385

Text #6

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.6318. Min Act: -0.1699

Data Index: 5657287 (Open Web Text)

Max Activating Token Index: 58

Text #7

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.6117. Min Act: -0.1694

Data Index: 6447547 (Open Web Text)

Max Activating Token Index: 46

Text #8

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.6135. Min Act: -0.1699

Data Index: 2809169 (Open Web Text)

Max Activating Token Index: 140

Text #9

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.6142. Min Act: -0.1700

Data Index: 1897942 (Open Web Text)

Max Activating Token Index: 320

Text #10

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.6000. Min Act: -0.1700

Data Index: 4614599 (Open Web Text)

Max Activating Token Index: 613

Text #11

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.5935. Min Act: -0.1699

Data Index: 7189192 (Open Web Text)

Max Activating Token Index: 442

Text #12

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.5986. Min Act: -0.1700

Data Index: 6365428 (Open Web Text)

Max Activating Token Index: 222

Text #13

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.6028. Min Act: -0.1697

Data Index: 5189459 (Open Web Text)

Max Activating Token Index: 198

Text #14

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.5896. Min Act: -0.1698

Data Index: 6432989 (Open Web Text)

Max Activating Token Index: 460

Text #15

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.5905. Min Act: -0.1699

Data Index: 2858886 (Open Web Text)

Max Activating Token Index: 41

Text #16

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.5910. Min Act: -0.1700

Data Index: 1778103 (Open Web Text)

Max Activating Token Index: 436

Text #17

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.5860. Min Act: -0.1700

Data Index: 4358653 (Open Web Text)

Max Activating Token Index: 820

Text #18

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.5929. Min Act: -0.1698

Data Index: 5767506 (Open Web Text)

Max Activating Token Index: 391

Text #19

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.5808. Min Act: -0.1699

Data Index: 3281660 (Open Web Text)

Max Activating Token Index: 362