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

Dataset: Open Web Text

Neuron 860 in Layer 4

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: 3.6992. Min Range: -3.6992

Max Act: 3.6992. Min Act: -0.1700

Data Index: 1802940 (Open Web Text)

Max Activating Token Index: 686

Text #1

Max Range: 3.6992. Min Range: -3.6992

Max Act: 3.6598. Min Act: -0.1700

Data Index: 5649515 (Open Web Text)

Max Activating Token Index: 272

Text #2

Max Range: 3.6992. Min Range: -3.6992

Max Act: 3.6001. Min Act: -0.1700

Data Index: 6283214 (Open Web Text)

Max Activating Token Index: 946

Text #3

Max Range: 3.6992. Min Range: -3.6992

Max Act: 3.5935. Min Act: -0.1700

Data Index: 1801519 (Open Web Text)

Max Activating Token Index: 582

Text #4

Max Range: 3.6992. Min Range: -3.6992

Max Act: 3.5755. Min Act: -0.1700

Data Index: 2222873 (Open Web Text)

Max Activating Token Index: 770

Text #5

Max Range: 3.6992. Min Range: -3.6992

Max Act: 3.5865. Min Act: -0.1700

Data Index: 7040334 (Open Web Text)

Max Activating Token Index: 701

Text #6

Max Range: 3.6992. Min Range: -3.6992

Max Act: 3.5424. Min Act: -0.1700

Data Index: 724256 (Open Web Text)

Max Activating Token Index: 953

Text #7

Max Range: 3.6992. Min Range: -3.6992

Max Act: 3.5520. Min Act: -0.1700

Data Index: 8721184 (Open Web Text)

Max Activating Token Index: 695

Text #8

Max Range: 3.6992. Min Range: -3.6992

Max Act: 3.5805. Min Act: -0.1700

Data Index: 386080 (Open Web Text)

Max Activating Token Index: 470

Text #9

Max Range: 3.6992. Min Range: -3.6992

Max Act: 3.5668. Min Act: -0.1700

Data Index: 6611254 (Open Web Text)

Max Activating Token Index: 605

Text #10

Max Range: 3.6992. Min Range: -3.6992

Max Act: 3.5629. Min Act: -0.1700

Data Index: 2393266 (Open Web Text)

Max Activating Token Index: 464

Text #11

Max Range: 3.6992. Min Range: -3.6992

Max Act: 3.5678. Min Act: -0.1700

Data Index: 3016529 (Open Web Text)

Max Activating Token Index: 366

Text #12

Max Range: 3.6992. Min Range: -3.6992

Max Act: 3.5438. Min Act: -0.1700

Data Index: 4946984 (Open Web Text)

Max Activating Token Index: 979

Text #13

Max Range: 3.6992. Min Range: -3.6992

Max Act: 3.5368. Min Act: -0.1700

Data Index: 7302367 (Open Web Text)

Max Activating Token Index: 985

Text #14

Max Range: 3.6992. Min Range: -3.6992

Max Act: 3.5474. Min Act: -0.1700

Data Index: 8750157 (Open Web Text)

Max Activating Token Index: 390

Text #15

Max Range: 3.6992. Min Range: -3.6992

Max Act: 3.5206. Min Act: -0.1700

Data Index: 3941160 (Open Web Text)

Max Activating Token Index: 219

Text #16

Max Range: 3.6992. Min Range: -3.6992

Max Act: 3.5249. Min Act: -0.1700

Data Index: 7991560 (Open Web Text)

Max Activating Token Index: 341

Text #17

Max Range: 3.6992. Min Range: -3.6992

Max Act: 3.5213. Min Act: -0.1700

Data Index: 7324743 (Open Web Text)

Max Activating Token Index: 657

Text #18

Max Range: 3.6992. Min Range: -3.6992

Max Act: 3.5341. Min Act: -0.1700

Data Index: 4101613 (Open Web Text)

Max Activating Token Index: 304

Text #19

Max Range: 3.6992. Min Range: -3.6992

Max Act: 3.5240. Min Act: -0.1700

Data Index: 4405737 (Open Web Text)

Max Activating Token Index: 587