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

Dataset: Open Web Text

Neuron 2252 in Layer 6

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: 4.3731. Min Range: -4.3731

Max Act: 4.3731. Min Act: -0.1700

Data Index: 6294888 (Open Web Text)

Max Activating Token Index: 867

Text #1

Max Range: 4.3731. Min Range: -4.3731

Max Act: 4.2040. Min Act: -0.1700

Data Index: 1308683 (Open Web Text)

Max Activating Token Index: 430

Text #2

Max Range: 4.3731. Min Range: -4.3731

Max Act: 4.2436. Min Act: -0.1700

Data Index: 7635963 (Open Web Text)

Max Activating Token Index: 27

Text #3

Max Range: 4.3731. Min Range: -4.3731

Max Act: 4.2082. Min Act: -0.1700

Data Index: 4957322 (Open Web Text)

Max Activating Token Index: 915

Text #4

Max Range: 4.3731. Min Range: -4.3731

Max Act: 4.1808. Min Act: -0.1700

Data Index: 3951598 (Open Web Text)

Max Activating Token Index: 715

Text #5

Max Range: 4.3731. Min Range: -4.3731

Max Act: 4.1983. Min Act: -0.1700

Data Index: 4672803 (Open Web Text)

Max Activating Token Index: 526

Text #6

Max Range: 4.3731. Min Range: -4.3731

Max Act: 4.1583. Min Act: -0.1700

Data Index: 8139886 (Open Web Text)

Max Activating Token Index: 401

Text #7

Max Range: 4.3731. Min Range: -4.3731

Max Act: 4.1675. Min Act: -0.1700

Data Index: 5371046 (Open Web Text)

Max Activating Token Index: 230

Text #8

Max Range: 4.3731. Min Range: -4.3731

Max Act: 4.1713. Min Act: -0.1700

Data Index: 3753177 (Open Web Text)

Max Activating Token Index: 903

Text #9

Max Range: 4.3731. Min Range: -4.3731

Max Act: 4.1568. Min Act: -0.1700

Data Index: 6477193 (Open Web Text)

Max Activating Token Index: 66

Text #10

Max Range: 4.3731. Min Range: -4.3731

Max Act: 4.1731. Min Act: -0.1700

Data Index: 8391381 (Open Web Text)

Max Activating Token Index: 311

Text #11

Max Range: 4.3731. Min Range: -4.3731

Max Act: 4.1150. Min Act: -0.1700

Data Index: 7624485 (Open Web Text)

Max Activating Token Index: 537

Text #12

Max Range: 4.3731. Min Range: -4.3731

Max Act: 4.0915. Min Act: -0.1700

Data Index: 1172818 (Open Web Text)

Max Activating Token Index: 11

Text #13

Max Range: 4.3731. Min Range: -4.3731

Max Act: 4.0988. Min Act: -0.1700

Data Index: 4099830 (Open Web Text)

Max Activating Token Index: 701

Text #14

Max Range: 4.3731. Min Range: -4.3731

Max Act: 4.1198. Min Act: -0.1700

Data Index: 2245688 (Open Web Text)

Max Activating Token Index: 84

Text #15

Max Range: 4.3731. Min Range: -4.3731

Max Act: 4.1232. Min Act: -0.1700

Data Index: 1428955 (Open Web Text)

Max Activating Token Index: 121

Text #16

Max Range: 4.3731. Min Range: -4.3731

Max Act: 4.0943. Min Act: -0.1700

Data Index: 6599793 (Open Web Text)

Max Activating Token Index: 864

Text #17

Max Range: 4.3731. Min Range: -4.3731

Max Act: 4.0618. Min Act: -0.1700

Data Index: 5740502 (Open Web Text)

Max Activating Token Index: 537

Text #18

Max Range: 4.3731. Min Range: -4.3731

Max Act: 4.0658. Min Act: -0.1700

Data Index: 2386555 (Open Web Text)

Max Activating Token Index: 654

Text #19

Max Range: 4.3731. Min Range: -4.3731

Max Act: 4.0744. Min Act: -0.1700

Data Index: 7200356 (Open Web Text)

Max Activating Token Index: 80