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

Dataset: Open Web Text

Neuron 2225 in Layer 5

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: 2.5581. Min Range: -2.5581

Max Act: 2.5581. Min Act: -0.1700

Data Index: 5718281 (Open Web Text)

Max Activating Token Index: 520

Text #1

Max Range: 2.5581. Min Range: -2.5581

Max Act: 2.5204. Min Act: -0.1700

Data Index: 5583872 (Open Web Text)

Max Activating Token Index: 718

Text #2

Max Range: 2.5581. Min Range: -2.5581

Max Act: 2.4823. Min Act: -0.1700

Data Index: 8266815 (Open Web Text)

Max Activating Token Index: 656

Text #3

Max Range: 2.5581. Min Range: -2.5581

Max Act: 2.4851. Min Act: -0.1700

Data Index: 5896024 (Open Web Text)

Max Activating Token Index: 721

Text #4

Max Range: 2.5581. Min Range: -2.5581

Max Act: 2.4424. Min Act: -0.1700

Data Index: 2817282 (Open Web Text)

Max Activating Token Index: 724

Text #5

Max Range: 2.5581. Min Range: -2.5581

Max Act: 2.4583. Min Act: -0.1700

Data Index: 6729130 (Open Web Text)

Max Activating Token Index: 622

Text #6

Max Range: 2.5581. Min Range: -2.5581

Max Act: 2.4634. Min Act: -0.1700

Data Index: 3087907 (Open Web Text)

Max Activating Token Index: 235

Text #7

Max Range: 2.5581. Min Range: -2.5581

Max Act: 2.4567. Min Act: -0.1700

Data Index: 2327457 (Open Web Text)

Max Activating Token Index: 375

Text #8

Max Range: 2.5581. Min Range: -2.5581

Max Act: 2.4341. Min Act: -0.1700

Data Index: 6819755 (Open Web Text)

Max Activating Token Index: 120

Text #9

Max Range: 2.5581. Min Range: -2.5581

Max Act: 2.4236. Min Act: -0.1700

Data Index: 6299967 (Open Web Text)

Max Activating Token Index: 948

Text #10

Max Range: 2.5581. Min Range: -2.5581

Max Act: 2.4217. Min Act: -0.1700

Data Index: 6842384 (Open Web Text)

Max Activating Token Index: 605

Text #11

Max Range: 2.5581. Min Range: -2.5581

Max Act: 2.4141. Min Act: -0.1700

Data Index: 294463 (Open Web Text)

Max Activating Token Index: 589

Text #12

Max Range: 2.5581. Min Range: -2.5581

Max Act: 2.3976. Min Act: -0.1700

Data Index: 2814384 (Open Web Text)

Max Activating Token Index: 355

Text #13

Max Range: 2.5581. Min Range: -2.5581

Max Act: 2.4057. Min Act: -0.1700

Data Index: 4615307 (Open Web Text)

Max Activating Token Index: 389

Text #14

Max Range: 2.5581. Min Range: -2.5581

Max Act: 2.3685. Min Act: -0.1700

Data Index: 6989086 (Open Web Text)

Max Activating Token Index: 427

Text #15

Max Range: 2.5581. Min Range: -2.5581

Max Act: 2.3739. Min Act: -0.1700

Data Index: 4245375 (Open Web Text)

Max Activating Token Index: 914

Text #16

Max Range: 2.5581. Min Range: -2.5581

Max Act: 2.3659. Min Act: -0.1700

Data Index: 5972266 (Open Web Text)

Max Activating Token Index: 118

Text #17

Max Range: 2.5581. Min Range: -2.5581

Max Act: 2.3656. Min Act: -0.1700

Data Index: 6729122 (Open Web Text)

Max Activating Token Index: 384

Text #18

Max Range: 2.5581. Min Range: -2.5581

Max Act: 2.3841. Min Act: -0.1700

Data Index: 4129810 (Open Web Text)

Max Activating Token Index: 403

Text #19

Max Range: 2.5581. Min Range: -2.5581

Max Act: 2.3660. Min Act: -0.1700

Data Index: 6299966 (Open Web Text)

Max Activating Token Index: 384