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

Dataset: Open Web Text

Neuron 1387 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: 3.3082. Min Range: -3.3082

Max Act: 3.3082. Min Act: -0.1700

Data Index: 8088212 (Open Web Text)

Max Activating Token Index: 14

Text #1

Max Range: 3.3082. Min Range: -3.3082

Max Act: 3.2005. Min Act: -0.1700

Data Index: 4118288 (Open Web Text)

Max Activating Token Index: 457

Text #2

Max Range: 3.3082. Min Range: -3.3082

Max Act: 3.2212. Min Act: -0.1700

Data Index: 3090371 (Open Web Text)

Max Activating Token Index: 745

Text #3

Max Range: 3.3082. Min Range: -3.3082

Max Act: 3.1781. Min Act: -0.1700

Data Index: 5151228 (Open Web Text)

Max Activating Token Index: 759

Text #4

Max Range: 3.3082. Min Range: -3.3082

Max Act: 3.2394. Min Act: -0.1700

Data Index: 7409553 (Open Web Text)

Max Activating Token Index: 990

Text #5

Max Range: 3.3082. Min Range: -3.3082

Max Act: 3.2317. Min Act: -0.1700

Data Index: 3050996 (Open Web Text)

Max Activating Token Index: 841

Text #6

Max Range: 3.3082. Min Range: -3.3082

Max Act: 3.2071. Min Act: -0.1700

Data Index: 1852266 (Open Web Text)

Max Activating Token Index: 958

Text #7

Max Range: 3.3082. Min Range: -3.3082

Max Act: 3.2179. Min Act: -0.1700

Data Index: 4507239 (Open Web Text)

Max Activating Token Index: 621

Text #8

Max Range: 3.3082. Min Range: -3.3082

Max Act: 3.1860. Min Act: -0.1700

Data Index: 2777645 (Open Web Text)

Max Activating Token Index: 50

Text #9

Max Range: 3.3082. Min Range: -3.3082

Max Act: 3.1396. Min Act: -0.1700

Data Index: 8799384 (Open Web Text)

Max Activating Token Index: 391

Text #10

Max Range: 3.3082. Min Range: -3.3082

Max Act: 3.1503. Min Act: -0.1700

Data Index: 1103914 (Open Web Text)

Max Activating Token Index: 40

Text #11

Max Range: 3.3082. Min Range: -3.3082

Max Act: 3.1480. Min Act: -0.1700

Data Index: 4116498 (Open Web Text)

Max Activating Token Index: 1009

Text #12

Max Range: 3.3082. Min Range: -3.3082

Max Act: 3.1200. Min Act: -0.1700

Data Index: 7093863 (Open Web Text)

Max Activating Token Index: 435

Text #13

Max Range: 3.3082. Min Range: -3.3082

Max Act: 3.1676. Min Act: -0.1700

Data Index: 60152 (Open Web Text)

Max Activating Token Index: 551

Text #14

Max Range: 3.3082. Min Range: -3.3082

Max Act: 3.1367. Min Act: -0.1700

Data Index: 7198076 (Open Web Text)

Max Activating Token Index: 621

Text #15

Max Range: 3.3082. Min Range: -3.3082

Max Act: 3.1042. Min Act: -0.1700

Data Index: 7435939 (Open Web Text)

Max Activating Token Index: 869

Text #16

Max Range: 3.3082. Min Range: -3.3082

Max Act: 3.1092. Min Act: -0.1700

Data Index: 3352403 (Open Web Text)

Max Activating Token Index: 917

Text #17

Max Range: 3.3082. Min Range: -3.3082

Max Act: 3.1056. Min Act: -0.1700

Data Index: 7369521 (Open Web Text)

Max Activating Token Index: 390

Text #18

Max Range: 3.3082. Min Range: -3.3082

Max Act: 3.1174. Min Act: -0.1700

Data Index: 3796842 (Open Web Text)

Max Activating Token Index: 995

Text #19

Max Range: 3.3082. Min Range: -3.3082

Max Act: 3.1243. Min Act: -0.1700

Data Index: 5089871 (Open Web Text)

Max Activating Token Index: 774