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

Dataset: Open Web Text

Neuron 2427 in Layer 3

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: 4.2345. Min Range: -4.2345

Max Act: 4.2345. Min Act: -0.1700

Data Index: 3336495 (Open Web Text)

Max Activating Token Index: 435

Text #1

Max Range: 4.2345. Min Range: -4.2345

Max Act: 4.1913. Min Act: -0.1700

Data Index: 8426639 (Open Web Text)

Max Activating Token Index: 947

Text #2

Max Range: 4.2345. Min Range: -4.2345

Max Act: 4.1771. Min Act: -0.1700

Data Index: 3218952 (Open Web Text)

Max Activating Token Index: 929

Text #3

Max Range: 4.2345. Min Range: -4.2345

Max Act: 4.1932. Min Act: -0.1700

Data Index: 8494735 (Open Web Text)

Max Activating Token Index: 556

Text #4

Max Range: 4.2345. Min Range: -4.2345

Max Act: 4.1311. Min Act: -0.1700

Data Index: 3691892 (Open Web Text)

Max Activating Token Index: 377

Text #5

Max Range: 4.2345. Min Range: -4.2345

Max Act: 4.1363. Min Act: -0.1700

Data Index: 5575041 (Open Web Text)

Max Activating Token Index: 495

Text #6

Max Range: 4.2345. Min Range: -4.2345

Max Act: 4.1266. Min Act: -0.1700

Data Index: 157816 (Open Web Text)

Max Activating Token Index: 725

Text #7

Max Range: 4.2345. Min Range: -4.2345

Max Act: 4.1028. Min Act: -0.1700

Data Index: 7735746 (Open Web Text)

Max Activating Token Index: 738

Text #8

Max Range: 4.2345. Min Range: -4.2345

Max Act: 4.0798. Min Act: -0.1700

Data Index: 7394293 (Open Web Text)

Max Activating Token Index: 621

Text #9

Max Range: 4.2345. Min Range: -4.2345

Max Act: 4.0993. Min Act: -0.1700

Data Index: 4067077 (Open Web Text)

Max Activating Token Index: 302

Text #10

Max Range: 4.2345. Min Range: -4.2345

Max Act: 4.1105. Min Act: -0.1700

Data Index: 3888013 (Open Web Text)

Max Activating Token Index: 103

Text #11

Max Range: 4.2345. Min Range: -4.2345

Max Act: 4.1095. Min Act: -0.1700

Data Index: 1631201 (Open Web Text)

Max Activating Token Index: 767

Text #12

Max Range: 4.2345. Min Range: -4.2345

Max Act: 4.0812. Min Act: -0.1700

Data Index: 7512732 (Open Web Text)

Max Activating Token Index: 931

Text #13

Max Range: 4.2345. Min Range: -4.2345

Max Act: 4.0687. Min Act: -0.1700

Data Index: 5071798 (Open Web Text)

Max Activating Token Index: 173

Text #14

Max Range: 4.2345. Min Range: -4.2345

Max Act: 4.0335. Min Act: -0.1700

Data Index: 4353930 (Open Web Text)

Max Activating Token Index: 148

Text #15

Max Range: 4.2345. Min Range: -4.2345

Max Act: 4.0319. Min Act: -0.1700

Data Index: 2769865 (Open Web Text)

Max Activating Token Index: 619

Text #16

Max Range: 4.2345. Min Range: -4.2345

Max Act: 4.0391. Min Act: -0.1700

Data Index: 3106585 (Open Web Text)

Max Activating Token Index: 789

Text #17

Max Range: 4.2345. Min Range: -4.2345

Max Act: 4.0456. Min Act: -0.1700

Data Index: 1950580 (Open Web Text)

Max Activating Token Index: 518

Text #18

Max Range: 4.2345. Min Range: -4.2345

Max Act: 4.0235. Min Act: -0.1700

Data Index: 5868899 (Open Web Text)

Max Activating Token Index: 511

Text #19

Max Range: 4.2345. Min Range: -4.2345

Max Act: 4.0400. Min Act: -0.1700

Data Index: 4381157 (Open Web Text)

Max Activating Token Index: 559