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

Dataset: Open Web Text

Neuron 2660 in Layer 1

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: 3.8934. Min Range: -3.8934

Max Act: 3.8934. Min Act: -0.1700

Data Index: 335462 (Open Web Text)

Max Activating Token Index: 10

Text #1

Max Range: 3.8934. Min Range: -3.8934

Max Act: 3.8412. Min Act: -0.1700

Data Index: 6953944 (Open Web Text)

Max Activating Token Index: 572

Text #2

Max Range: 3.8934. Min Range: -3.8934

Max Act: 3.8173. Min Act: -0.1700

Data Index: 8526907 (Open Web Text)

Max Activating Token Index: 932

Text #3

Max Range: 3.8934. Min Range: -3.8934

Max Act: 3.8008. Min Act: -0.1700

Data Index: 5670045 (Open Web Text)

Max Activating Token Index: 154

Text #4

Max Range: 3.8934. Min Range: -3.8934

Max Act: 3.8395. Min Act: -0.1700

Data Index: 210589 (Open Web Text)

Max Activating Token Index: 13

Text #5

Max Range: 3.8934. Min Range: -3.8934

Max Act: 3.8055. Min Act: -0.1700

Data Index: 1229054 (Open Web Text)

Max Activating Token Index: 42

Text #6

Max Range: 3.8934. Min Range: -3.8934

Max Act: 3.8167. Min Act: -0.1700

Data Index: 3363617 (Open Web Text)

Max Activating Token Index: 482

Text #7

Max Range: 3.8934. Min Range: -3.8934

Max Act: 3.7824. Min Act: -0.1700

Data Index: 5660242 (Open Web Text)

Max Activating Token Index: 448

Text #8

Max Range: 3.8934. Min Range: -3.8934

Max Act: 3.7410. Min Act: -0.1700

Data Index: 1469718 (Open Web Text)

Max Activating Token Index: 504

Text #9

Max Range: 3.8934. Min Range: -3.8934

Max Act: 3.7609. Min Act: -0.1700

Data Index: 8597615 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 3.8934. Min Range: -3.8934

Max Act: 3.7315. Min Act: -0.1700

Data Index: 1136345 (Open Web Text)

Max Activating Token Index: 13

Text #11

Max Range: 3.8934. Min Range: -3.8934

Max Act: 3.7547. Min Act: -0.1700

Data Index: 4573148 (Open Web Text)

Max Activating Token Index: 339

Text #12

Max Range: 3.8934. Min Range: -3.8934

Max Act: 3.7780. Min Act: -0.1700

Data Index: 7618093 (Open Web Text)

Max Activating Token Index: 681

Text #13

Max Range: 3.8934. Min Range: -3.8934

Max Act: 3.7375. Min Act: -0.1700

Data Index: 2310735 (Open Web Text)

Max Activating Token Index: 680

Text #14

Max Range: 3.8934. Min Range: -3.8934

Max Act: 3.7326. Min Act: -0.1700

Data Index: 2481767 (Open Web Text)

Max Activating Token Index: 377

Text #15

Max Range: 3.8934. Min Range: -3.8934

Max Act: 3.7101. Min Act: -0.1700

Data Index: 1140669 (Open Web Text)

Max Activating Token Index: 938

Text #16

Max Range: 3.8934. Min Range: -3.8934

Max Act: 3.7282. Min Act: -0.1700

Data Index: 2621453 (Open Web Text)

Max Activating Token Index: 421

Text #17

Max Range: 3.8934. Min Range: -3.8934

Max Act: 3.7245. Min Act: -0.1700

Data Index: 3010605 (Open Web Text)

Max Activating Token Index: 601

Text #18

Max Range: 3.8934. Min Range: -3.8934

Max Act: 3.7545. Min Act: -0.1700

Data Index: 124022 (Open Web Text)

Max Activating Token Index: 520

Text #19

Max Range: 3.8934. Min Range: -3.8934

Max Act: 3.7157. Min Act: -0.1700

Data Index: 3411135 (Open Web Text)

Max Activating Token Index: 19