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

Dataset: Open Web Text

Neuron 624 in Layer 5

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: 3.5109. Min Range: -3.5109

Max Act: 3.5109. Min Act: -0.1700

Data Index: 3396685 (Open Web Text)

Max Activating Token Index: 169

Text #1

Max Range: 3.5109. Min Range: -3.5109

Max Act: 3.3282. Min Act: -0.1700

Data Index: 1367734 (Open Web Text)

Max Activating Token Index: 515

Text #2

Max Range: 3.5109. Min Range: -3.5109

Max Act: 3.3439. Min Act: -0.1700

Data Index: 4658676 (Open Web Text)

Max Activating Token Index: 463

Text #3

Max Range: 3.5109. Min Range: -3.5109

Max Act: 3.2698. Min Act: -0.1700

Data Index: 2564361 (Open Web Text)

Max Activating Token Index: 736

Text #4

Max Range: 3.5109. Min Range: -3.5109

Max Act: 3.2640. Min Act: -0.1700

Data Index: 7825408 (Open Web Text)

Max Activating Token Index: 188

Text #5

Max Range: 3.5109. Min Range: -3.5109

Max Act: 3.2553. Min Act: -0.1700

Data Index: 3203913 (Open Web Text)

Max Activating Token Index: 453

Text #6

Max Range: 3.5109. Min Range: -3.5109

Max Act: 3.2482. Min Act: -0.1700

Data Index: 1626264 (Open Web Text)

Max Activating Token Index: 653

Text #7

Max Range: 3.5109. Min Range: -3.5109

Max Act: 3.2344. Min Act: -0.1700

Data Index: 6071320 (Open Web Text)

Max Activating Token Index: 809

Text #8

Max Range: 3.5109. Min Range: -3.5109

Max Act: 3.2661. Min Act: -0.1700

Data Index: 676339 (Open Web Text)

Max Activating Token Index: 788

Text #9

Max Range: 3.5109. Min Range: -3.5109

Max Act: 3.1888. Min Act: -0.1700

Data Index: 7527253 (Open Web Text)

Max Activating Token Index: 926

Text #10

Max Range: 3.5109. Min Range: -3.5109

Max Act: 3.2141. Min Act: -0.1700

Data Index: 6605136 (Open Web Text)

Max Activating Token Index: 591

Text #11

Max Range: 3.5109. Min Range: -3.5109

Max Act: 3.1905. Min Act: -0.1700

Data Index: 6799923 (Open Web Text)

Max Activating Token Index: 409

Text #12

Max Range: 3.5109. Min Range: -3.5109

Max Act: 3.1722. Min Act: -0.1700

Data Index: 7718472 (Open Web Text)

Max Activating Token Index: 762

Text #13

Max Range: 3.5109. Min Range: -3.5109

Max Act: 3.1772. Min Act: -0.1700

Data Index: 4660963 (Open Web Text)

Max Activating Token Index: 984

Text #14

Max Range: 3.5109. Min Range: -3.5109

Max Act: 3.1510. Min Act: -0.1700

Data Index: 7050839 (Open Web Text)

Max Activating Token Index: 98

Text #15

Max Range: 3.5109. Min Range: -3.5109

Max Act: 3.1159. Min Act: -0.1700

Data Index: 6650421 (Open Web Text)

Max Activating Token Index: 307

Text #16

Max Range: 3.5109. Min Range: -3.5109

Max Act: 3.1299. Min Act: -0.1700

Data Index: 3718525 (Open Web Text)

Max Activating Token Index: 910

Text #17

Max Range: 3.5109. Min Range: -3.5109

Max Act: 3.1123. Min Act: -0.1700

Data Index: 2014733 (Open Web Text)

Max Activating Token Index: 333

Text #18

Max Range: 3.5109. Min Range: -3.5109

Max Act: 3.1071. Min Act: -0.1700

Data Index: 5084620 (Open Web Text)

Max Activating Token Index: 556

Text #19

Max Range: 3.5109. Min Range: -3.5109

Max Act: 3.1094. Min Act: -0.1700

Data Index: 3625231 (Open Web Text)

Max Activating Token Index: 169