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

Dataset: Open Web Text

Neuron 3020 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: 5.5027. Min Range: -5.5027

Max Act: 5.5024. Min Act: -0.1700

Data Index: 2938315 (Open Web Text)

Max Activating Token Index: 887

Text #1

Max Range: 5.5027. Min Range: -5.5027

Max Act: 5.5027. Min Act: -0.1700

Data Index: 5632640 (Open Web Text)

Max Activating Token Index: 875

Text #2

Max Range: 5.5027. Min Range: -5.5027

Max Act: 5.4834. Min Act: -0.1700

Data Index: 1832060 (Open Web Text)

Max Activating Token Index: 985

Text #3

Max Range: 5.5027. Min Range: -5.5027

Max Act: 5.4297. Min Act: -0.1700

Data Index: 4983736 (Open Web Text)

Max Activating Token Index: 350

Text #4

Max Range: 5.5027. Min Range: -5.5027

Max Act: 5.4668. Min Act: -0.1700

Data Index: 6464731 (Open Web Text)

Max Activating Token Index: 840

Text #5

Max Range: 5.5027. Min Range: -5.5027

Max Act: 5.4447. Min Act: -0.1700

Data Index: 1994128 (Open Web Text)

Max Activating Token Index: 325

Text #6

Max Range: 5.5027. Min Range: -5.5027

Max Act: 5.3947. Min Act: -0.1700

Data Index: 3208454 (Open Web Text)

Max Activating Token Index: 187

Text #7

Max Range: 5.5027. Min Range: -5.5027

Max Act: 5.3833. Min Act: -0.1700

Data Index: 565320 (Open Web Text)

Max Activating Token Index: 795

Text #8

Max Range: 5.5027. Min Range: -5.5027

Max Act: 5.4308. Min Act: -0.1700

Data Index: 4127172 (Open Web Text)

Max Activating Token Index: 413

Text #9

Max Range: 5.5027. Min Range: -5.5027

Max Act: 5.3830. Min Act: -0.1700

Data Index: 6171474 (Open Web Text)

Max Activating Token Index: 399

Text #10

Max Range: 5.5027. Min Range: -5.5027

Max Act: 5.3713. Min Act: -0.1700

Data Index: 1472090 (Open Web Text)

Max Activating Token Index: 458

Text #11

Max Range: 5.5027. Min Range: -5.5027

Max Act: 5.4135. Min Act: -0.1700

Data Index: 6816941 (Open Web Text)

Max Activating Token Index: 183

Text #12

Max Range: 5.5027. Min Range: -5.5027

Max Act: 5.3676. Min Act: -0.1700

Data Index: 8517322 (Open Web Text)

Max Activating Token Index: 36

Text #13

Max Range: 5.5027. Min Range: -5.5027

Max Act: 5.3843. Min Act: -0.1700

Data Index: 7496873 (Open Web Text)

Max Activating Token Index: 461

Text #14

Max Range: 5.5027. Min Range: -5.5027

Max Act: 5.3566. Min Act: -0.1700

Data Index: 4086238 (Open Web Text)

Max Activating Token Index: 475

Text #15

Max Range: 5.5027. Min Range: -5.5027

Max Act: 5.3598. Min Act: -0.1700

Data Index: 707736 (Open Web Text)

Max Activating Token Index: 397

Text #16

Max Range: 5.5027. Min Range: -5.5027

Max Act: 5.3536. Min Act: -0.1700

Data Index: 874438 (Open Web Text)

Max Activating Token Index: 45

Text #17

Max Range: 5.5027. Min Range: -5.5027

Max Act: 5.3515. Min Act: -0.1700

Data Index: 4570274 (Open Web Text)

Max Activating Token Index: 344

Text #18

Max Range: 5.5027. Min Range: -5.5027

Max Act: 5.3729. Min Act: -0.1700

Data Index: 3354345 (Open Web Text)

Max Activating Token Index: 352

Text #19

Max Range: 5.5027. Min Range: -5.5027

Max Act: 5.3533. Min Act: -0.1700

Data Index: 3211175 (Open Web Text)

Max Activating Token Index: 168