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

Dataset: Open Web Text

Neuron 1178 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: 5.7675. Min Range: -5.7675

Max Act: 5.7675. Min Act: -0.1700

Data Index: 1472927 (Open Web Text)

Max Activating Token Index: 118

Text #1

Max Range: 5.7675. Min Range: -5.7675

Max Act: 5.7634. Min Act: -0.1700

Data Index: 3267066 (Open Web Text)

Max Activating Token Index: 622

Text #2

Max Range: 5.7675. Min Range: -5.7675

Max Act: 5.6516. Min Act: -0.1700

Data Index: 2102935 (Open Web Text)

Max Activating Token Index: 491

Text #3

Max Range: 5.7675. Min Range: -5.7675

Max Act: 5.6272. Min Act: -0.1700

Data Index: 6468222 (Open Web Text)

Max Activating Token Index: 219

Text #4

Max Range: 5.7675. Min Range: -5.7675

Max Act: 5.5711. Min Act: -0.1700

Data Index: 1877902 (Open Web Text)

Max Activating Token Index: 828

Text #5

Max Range: 5.7675. Min Range: -5.7675

Max Act: 5.5336. Min Act: -0.1700

Data Index: 5640717 (Open Web Text)

Max Activating Token Index: 919

Text #6

Max Range: 5.7675. Min Range: -5.7675

Max Act: 5.4563. Min Act: -0.1700

Data Index: 6892867 (Open Web Text)

Max Activating Token Index: 948

Text #7

Max Range: 5.7675. Min Range: -5.7675

Max Act: 5.4454. Min Act: -0.1700

Data Index: 4920174 (Open Web Text)

Max Activating Token Index: 579

Text #8

Max Range: 5.7675. Min Range: -5.7675

Max Act: 5.4599. Min Act: -0.1700

Data Index: 593319 (Open Web Text)

Max Activating Token Index: 153

Text #9

Max Range: 5.7675. Min Range: -5.7675

Max Act: 5.3786. Min Act: -0.1700

Data Index: 3159144 (Open Web Text)

Max Activating Token Index: 812

Text #10

Max Range: 5.7675. Min Range: -5.7675

Max Act: 5.3112. Min Act: -0.1700

Data Index: 7891690 (Open Web Text)

Max Activating Token Index: 852

Text #11

Max Range: 5.7675. Min Range: -5.7675

Max Act: 5.3615. Min Act: -0.1700

Data Index: 8115681 (Open Web Text)

Max Activating Token Index: 305

Text #12

Max Range: 5.7675. Min Range: -5.7675

Max Act: 5.3194. Min Act: -0.1700

Data Index: 8029688 (Open Web Text)

Max Activating Token Index: 459

Text #13

Max Range: 5.7675. Min Range: -5.7675

Max Act: 5.2993. Min Act: -0.1700

Data Index: 6406282 (Open Web Text)

Max Activating Token Index: 186

Text #14

Max Range: 5.7675. Min Range: -5.7675

Max Act: 5.2531. Min Act: -0.1700

Data Index: 4666755 (Open Web Text)

Max Activating Token Index: 516

Text #15

Max Range: 5.7675. Min Range: -5.7675

Max Act: 5.2675. Min Act: -0.1700

Data Index: 8721838 (Open Web Text)

Max Activating Token Index: 483

Text #16

Max Range: 5.7675. Min Range: -5.7675

Max Act: 5.2558. Min Act: -0.1700

Data Index: 3606978 (Open Web Text)

Max Activating Token Index: 409

Text #17

Max Range: 5.7675. Min Range: -5.7675

Max Act: 5.1973. Min Act: -0.1700

Data Index: 186602 (Open Web Text)

Max Activating Token Index: 287

Text #18

Max Range: 5.7675. Min Range: -5.7675

Max Act: 5.2086. Min Act: -0.1700

Data Index: 6206397 (Open Web Text)

Max Activating Token Index: 962

Text #19

Max Range: 5.7675. Min Range: -5.7675

Max Act: 5.3165. Min Act: -0.1700

Data Index: 1887409 (Open Web Text)

Max Activating Token Index: 217