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

Dataset: Open Web Text

Neuron 1302 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: 3.3911. Min Range: -3.3911

Max Act: 3.3911. Min Act: -0.1700

Data Index: 3571601 (Open Web Text)

Max Activating Token Index: 556

Text #1

Max Range: 3.3911. Min Range: -3.3911

Max Act: 3.3239. Min Act: -0.1700

Data Index: 3063193 (Open Web Text)

Max Activating Token Index: 644

Text #2

Max Range: 3.3911. Min Range: -3.3911

Max Act: 3.3203. Min Act: -0.1700

Data Index: 3732992 (Open Web Text)

Max Activating Token Index: 167

Text #3

Max Range: 3.3911. Min Range: -3.3911

Max Act: 3.3121. Min Act: -0.1700

Data Index: 6823057 (Open Web Text)

Max Activating Token Index: 520

Text #4

Max Range: 3.3911. Min Range: -3.3911

Max Act: 3.3109. Min Act: -0.1700

Data Index: 2924053 (Open Web Text)

Max Activating Token Index: 286

Text #5

Max Range: 3.3911. Min Range: -3.3911

Max Act: 3.2819. Min Act: -0.1700

Data Index: 5778074 (Open Web Text)

Max Activating Token Index: 450

Text #6

Max Range: 3.3911. Min Range: -3.3911

Max Act: 3.2805. Min Act: -0.1700

Data Index: 4891955 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 3.3911. Min Range: -3.3911

Max Act: 3.2540. Min Act: -0.1700

Data Index: 3966903 (Open Web Text)

Max Activating Token Index: 52

Text #8

Max Range: 3.3911. Min Range: -3.3911

Max Act: 3.2685. Min Act: -0.1700

Data Index: 2019700 (Open Web Text)

Max Activating Token Index: 122

Text #9

Max Range: 3.3911. Min Range: -3.3911

Max Act: 3.2617. Min Act: -0.1700

Data Index: 1872970 (Open Web Text)

Max Activating Token Index: 340

Text #10

Max Range: 3.3911. Min Range: -3.3911

Max Act: 3.2561. Min Act: -0.1700

Data Index: 2021416 (Open Web Text)

Max Activating Token Index: 47

Text #11

Max Range: 3.3911. Min Range: -3.3911

Max Act: 3.2618. Min Act: -0.1700

Data Index: 8773160 (Open Web Text)

Max Activating Token Index: 28

Text #12

Max Range: 3.3911. Min Range: -3.3911

Max Act: 3.2495. Min Act: -0.1700

Data Index: 3827699 (Open Web Text)

Max Activating Token Index: 157

Text #13

Max Range: 3.3911. Min Range: -3.3911

Max Act: 3.2183. Min Act: -0.1700

Data Index: 3277159 (Open Web Text)

Max Activating Token Index: 1016

Text #14

Max Range: 3.3911. Min Range: -3.3911

Max Act: 3.2315. Min Act: -0.1700

Data Index: 6603561 (Open Web Text)

Max Activating Token Index: 369

Text #15

Max Range: 3.3911. Min Range: -3.3911

Max Act: 3.2680. Min Act: -0.1700

Data Index: 8695151 (Open Web Text)

Max Activating Token Index: 761

Text #16

Max Range: 3.3911. Min Range: -3.3911

Max Act: 3.2225. Min Act: -0.1700

Data Index: 5119128 (Open Web Text)

Max Activating Token Index: 867

Text #17

Max Range: 3.3911. Min Range: -3.3911

Max Act: 3.2319. Min Act: -0.1700

Data Index: 3252191 (Open Web Text)

Max Activating Token Index: 923

Text #18

Max Range: 3.3911. Min Range: -3.3911

Max Act: 3.1836. Min Act: -0.1700

Data Index: 7896453 (Open Web Text)

Max Activating Token Index: 98

Text #19

Max Range: 3.3911. Min Range: -3.3911

Max Act: 3.1239. Min Act: -0.1700

Data Index: 8344276 (Open Web Text)

Max Activating Token Index: 949