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

Dataset: Open Web Text

Neuron 2847 in Layer 0

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: 1.7225. Min Range: -1.7225

Max Act: 1.7225. Min Act: -0.1698

Data Index: 1131663 (Open Web Text)

Max Activating Token Index: 41

Text #1

Max Range: 1.7225. Min Range: -1.7225

Max Act: 1.6741. Min Act: -0.1698

Data Index: 5298741 (Open Web Text)

Max Activating Token Index: 605

Text #2

Max Range: 1.7225. Min Range: -1.7225

Max Act: 1.6588. Min Act: -0.1698

Data Index: 8807965 (Open Web Text)

Max Activating Token Index: 72

Text #3

Max Range: 1.7225. Min Range: -1.7225

Max Act: 1.6651. Min Act: -0.1698

Data Index: 6609677 (Open Web Text)

Max Activating Token Index: 79

Text #4

Max Range: 1.7225. Min Range: -1.7225

Max Act: 1.6397. Min Act: -0.1699

Data Index: 7880032 (Open Web Text)

Max Activating Token Index: 334

Text #5

Max Range: 1.7225. Min Range: -1.7225

Max Act: 1.6221. Min Act: -0.1700

Data Index: 3364740 (Open Web Text)

Max Activating Token Index: 52

Text #6

Max Range: 1.7225. Min Range: -1.7225

Max Act: 1.6184. Min Act: -0.1698

Data Index: 7691010 (Open Web Text)

Max Activating Token Index: 447

Text #7

Max Range: 1.7225. Min Range: -1.7225

Max Act: 1.6172. Min Act: -0.1700

Data Index: 789391 (Open Web Text)

Max Activating Token Index: 611

Text #8

Max Range: 1.7225. Min Range: -1.7225

Max Act: 1.6049. Min Act: -0.1700

Data Index: 2013089 (Open Web Text)

Max Activating Token Index: 380

Text #9

Max Range: 1.7225. Min Range: -1.7225

Max Act: 1.6054. Min Act: -0.1698

Data Index: 8738252 (Open Web Text)

Max Activating Token Index: 582

Text #10

Max Range: 1.7225. Min Range: -1.7225

Max Act: 1.6006. Min Act: -0.1699

Data Index: 554620 (Open Web Text)

Max Activating Token Index: 624

Text #11

Max Range: 1.7225. Min Range: -1.7225

Max Act: 1.6065. Min Act: -0.1698

Data Index: 8523926 (Open Web Text)

Max Activating Token Index: 310

Text #12

Max Range: 1.7225. Min Range: -1.7225

Max Act: 1.6053. Min Act: -0.1700

Data Index: 1413876 (Open Web Text)

Max Activating Token Index: 963

Text #13

Max Range: 1.7225. Min Range: -1.7225

Max Act: 1.6058. Min Act: -0.1700

Data Index: 1349648 (Open Web Text)

Max Activating Token Index: 33

Text #14

Max Range: 1.7225. Min Range: -1.7225

Max Act: 1.6075. Min Act: -0.1698

Data Index: 8799220 (Open Web Text)

Max Activating Token Index: 45

Text #15

Max Range: 1.7225. Min Range: -1.7225

Max Act: 1.6007. Min Act: -0.1699

Data Index: 6391078 (Open Web Text)

Max Activating Token Index: 245

Text #16

Max Range: 1.7225. Min Range: -1.7225

Max Act: 1.5977. Min Act: -0.1699

Data Index: 6065702 (Open Web Text)

Max Activating Token Index: 59

Text #17

Max Range: 1.7225. Min Range: -1.7225

Max Act: 1.5909. Min Act: -0.1700

Data Index: 4302171 (Open Web Text)

Max Activating Token Index: 562

Text #18

Max Range: 1.7225. Min Range: -1.7225

Max Act: 1.5821. Min Act: -0.1699

Data Index: 7910682 (Open Web Text)

Max Activating Token Index: 608

Text #19

Max Range: 1.7225. Min Range: -1.7225

Max Act: 1.5864. Min Act: -0.1700

Data Index: 8738253 (Open Web Text)

Max Activating Token Index: 211