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

Dataset: Open Web Text

Neuron 258 in Layer 2

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: 1.4055. Min Range: -1.4055

Max Act: 1.4055. Min Act: -0.1691

Data Index: 4006270 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 1.4055. Min Range: -1.4055

Max Act: 1.3609. Min Act: -0.1700

Data Index: 1870586 (Open Web Text)

Max Activating Token Index: 1005

Text #2

Max Range: 1.4055. Min Range: -1.4055

Max Act: 1.3421. Min Act: -0.1698

Data Index: 3238897 (Open Web Text)

Max Activating Token Index: 920

Text #3

Max Range: 1.4055. Min Range: -1.4055

Max Act: 1.3461. Min Act: -0.1688

Data Index: 1314176 (Open Web Text)

Max Activating Token Index: 448

Text #4

Max Range: 1.4055. Min Range: -1.4055

Max Act: 1.3285. Min Act: -0.1694

Data Index: 4666765 (Open Web Text)

Max Activating Token Index: 683

Text #5

Max Range: 1.4055. Min Range: -1.4055

Max Act: 1.3426. Min Act: -0.1695

Data Index: 2673570 (Open Web Text)

Max Activating Token Index: 988

Text #6

Max Range: 1.4055. Min Range: -1.4055

Max Act: 1.3330. Min Act: -0.1676

Data Index: 6218531 (Open Web Text)

Max Activating Token Index: 19

Text #7

Max Range: 1.4055. Min Range: -1.4055

Max Act: 1.3240. Min Act: -0.1700

Data Index: 1633474 (Open Web Text)

Max Activating Token Index: 35

Text #8

Max Range: 1.4055. Min Range: -1.4055

Max Act: 1.3229. Min Act: -0.1700

Data Index: 2093447 (Open Web Text)

Max Activating Token Index: 301

Text #9

Max Range: 1.4055. Min Range: -1.4055

Max Act: 1.3231. Min Act: -0.1699

Data Index: 667540 (Open Web Text)

Max Activating Token Index: 970

Text #10

Max Range: 1.4055. Min Range: -1.4055

Max Act: 1.3144. Min Act: -0.1658

Data Index: 6417981 (Open Web Text)

Max Activating Token Index: 827

Text #11

Max Range: 1.4055. Min Range: -1.4055

Max Act: 1.3280. Min Act: -0.1688

Data Index: 3357590 (Open Web Text)

Max Activating Token Index: 507

Text #12

Max Range: 1.4055. Min Range: -1.4055

Max Act: 1.3163. Min Act: -0.1697

Data Index: 8690149 (Open Web Text)

Max Activating Token Index: 96

Text #13

Max Range: 1.4055. Min Range: -1.4055

Max Act: 1.3035. Min Act: -0.1700

Data Index: 1849434 (Open Web Text)

Max Activating Token Index: 764

Text #14

Max Range: 1.4055. Min Range: -1.4055

Max Act: 1.3198. Min Act: -0.1700

Data Index: 1499987 (Open Web Text)

Max Activating Token Index: 818

Text #15

Max Range: 1.4055. Min Range: -1.4055

Max Act: 1.2993. Min Act: -0.1697

Data Index: 5046045 (Open Web Text)

Max Activating Token Index: 924

Text #16

Max Range: 1.4055. Min Range: -1.4055

Max Act: 1.2920. Min Act: -0.1696

Data Index: 7640691 (Open Web Text)

Max Activating Token Index: 652

Text #17

Max Range: 1.4055. Min Range: -1.4055

Max Act: 1.2926. Min Act: -0.1700

Data Index: 7530272 (Open Web Text)

Max Activating Token Index: 810

Text #18

Max Range: 1.4055. Min Range: -1.4055

Max Act: 1.3053. Min Act: -0.1700

Data Index: 4568321 (Open Web Text)

Max Activating Token Index: 20

Text #19

Max Range: 1.4055. Min Range: -1.4055

Max Act: 1.2974. Min Act: -0.1679

Data Index: 932355 (Open Web Text)

Max Activating Token Index: 481