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

Dataset: Open Web Text

Neuron 2645 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: 4.0960. Min Range: -4.0960

Max Act: 4.0960. Min Act: -0.1700

Data Index: 4518356 (Open Web Text)

Max Activating Token Index: 300

Text #1

Max Range: 4.0960. Min Range: -4.0960

Max Act: 4.0426. Min Act: -0.1700

Data Index: 1697958 (Open Web Text)

Max Activating Token Index: 164

Text #2

Max Range: 4.0960. Min Range: -4.0960

Max Act: 3.9418. Min Act: -0.1700

Data Index: 1593564 (Open Web Text)

Max Activating Token Index: 794

Text #3

Max Range: 4.0960. Min Range: -4.0960

Max Act: 3.8928. Min Act: -0.1700

Data Index: 4273961 (Open Web Text)

Max Activating Token Index: 762

Text #4

Max Range: 4.0960. Min Range: -4.0960

Max Act: 3.9076. Min Act: -0.1700

Data Index: 3989729 (Open Web Text)

Max Activating Token Index: 839

Text #5

Max Range: 4.0960. Min Range: -4.0960

Max Act: 3.8849. Min Act: -0.1700

Data Index: 3269520 (Open Web Text)

Max Activating Token Index: 209

Text #6

Max Range: 4.0960. Min Range: -4.0960

Max Act: 3.8467. Min Act: -0.1700

Data Index: 3116620 (Open Web Text)

Max Activating Token Index: 917

Text #7

Max Range: 4.0960. Min Range: -4.0960

Max Act: 3.8736. Min Act: -0.1700

Data Index: 4627511 (Open Web Text)

Max Activating Token Index: 319

Text #8

Max Range: 4.0960. Min Range: -4.0960

Max Act: 3.8243. Min Act: -0.1700

Data Index: 5846284 (Open Web Text)

Max Activating Token Index: 454

Text #9

Max Range: 4.0960. Min Range: -4.0960

Max Act: 3.8269. Min Act: -0.1700

Data Index: 2177706 (Open Web Text)

Max Activating Token Index: 785

Text #10

Max Range: 4.0960. Min Range: -4.0960

Max Act: 3.7987. Min Act: -0.1700

Data Index: 6661401 (Open Web Text)

Max Activating Token Index: 335

Text #11

Max Range: 4.0960. Min Range: -4.0960

Max Act: 3.7930. Min Act: -0.1700

Data Index: 1314070 (Open Web Text)

Max Activating Token Index: 315

Text #12

Max Range: 4.0960. Min Range: -4.0960

Max Act: 3.8150. Min Act: -0.1700

Data Index: 3837392 (Open Web Text)

Max Activating Token Index: 942

Text #13

Max Range: 4.0960. Min Range: -4.0960

Max Act: 3.8006. Min Act: -0.1700

Data Index: 8065007 (Open Web Text)

Max Activating Token Index: 413

Text #14

Max Range: 4.0960. Min Range: -4.0960

Max Act: 3.7885. Min Act: -0.1700

Data Index: 1165219 (Open Web Text)

Max Activating Token Index: 878

Text #15

Max Range: 4.0960. Min Range: -4.0960

Max Act: 3.7818. Min Act: -0.1700

Data Index: 6068212 (Open Web Text)

Max Activating Token Index: 311

Text #16

Max Range: 4.0960. Min Range: -4.0960

Max Act: 3.8093. Min Act: -0.1700

Data Index: 7315194 (Open Web Text)

Max Activating Token Index: 875

Text #17

Max Range: 4.0960. Min Range: -4.0960

Max Act: 3.8069. Min Act: -0.1700

Data Index: 1262254 (Open Web Text)

Max Activating Token Index: 337

Text #18

Max Range: 4.0960. Min Range: -4.0960

Max Act: 3.7596. Min Act: -0.1700

Data Index: 2531530 (Open Web Text)

Max Activating Token Index: 862

Text #19

Max Range: 4.0960. Min Range: -4.0960

Max Act: 3.7677. Min Act: -0.1700

Data Index: 332374 (Open Web Text)

Max Activating Token Index: 681