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

Dataset: Open Web Text

Neuron 36 in Layer 3

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: 3.0641. Min Range: -3.0641

Max Act: 3.0641. Min Act: -0.1700

Data Index: 4328160 (Open Web Text)

Max Activating Token Index: 708

Text #1

Max Range: 3.0641. Min Range: -3.0641

Max Act: 3.0408. Min Act: -0.1700

Data Index: 2795088 (Open Web Text)

Max Activating Token Index: 951

Text #2

Max Range: 3.0641. Min Range: -3.0641

Max Act: 3.0090. Min Act: -0.1700

Data Index: 3352998 (Open Web Text)

Max Activating Token Index: 462

Text #3

Max Range: 3.0641. Min Range: -3.0641

Max Act: 3.0105. Min Act: -0.1700

Data Index: 2265898 (Open Web Text)

Max Activating Token Index: 819

Text #4

Max Range: 3.0641. Min Range: -3.0641

Max Act: 2.9632. Min Act: -0.1700

Data Index: 3406353 (Open Web Text)

Max Activating Token Index: 909

Text #5

Max Range: 3.0641. Min Range: -3.0641

Max Act: 2.9506. Min Act: -0.1700

Data Index: 3073602 (Open Web Text)

Max Activating Token Index: 162

Text #6

Max Range: 3.0641. Min Range: -3.0641

Max Act: 2.9528. Min Act: -0.1700

Data Index: 3350152 (Open Web Text)

Max Activating Token Index: 267

Text #7

Max Range: 3.0641. Min Range: -3.0641

Max Act: 2.9457. Min Act: -0.1700

Data Index: 1492669 (Open Web Text)

Max Activating Token Index: 951

Text #8

Max Range: 3.0641. Min Range: -3.0641

Max Act: 2.9277. Min Act: -0.1700

Data Index: 7165902 (Open Web Text)

Max Activating Token Index: 273

Text #9

Max Range: 3.0641. Min Range: -3.0641

Max Act: 2.9281. Min Act: -0.1700

Data Index: 7620280 (Open Web Text)

Max Activating Token Index: 86

Text #10

Max Range: 3.0641. Min Range: -3.0641

Max Act: 2.9055. Min Act: -0.1700

Data Index: 3690547 (Open Web Text)

Max Activating Token Index: 16

Text #11

Max Range: 3.0641. Min Range: -3.0641

Max Act: 2.9183. Min Act: -0.1700

Data Index: 2314879 (Open Web Text)

Max Activating Token Index: 887

Text #12

Max Range: 3.0641. Min Range: -3.0641

Max Act: 2.8996. Min Act: -0.1700

Data Index: 8093689 (Open Web Text)

Max Activating Token Index: 179

Text #13

Max Range: 3.0641. Min Range: -3.0641

Max Act: 2.9050. Min Act: -0.1700

Data Index: 6588492 (Open Web Text)

Max Activating Token Index: 622

Text #14

Max Range: 3.0641. Min Range: -3.0641

Max Act: 2.8844. Min Act: -0.1700

Data Index: 2202511 (Open Web Text)

Max Activating Token Index: 427

Text #15

Max Range: 3.0641. Min Range: -3.0641

Max Act: 2.8919. Min Act: -0.1700

Data Index: 1551751 (Open Web Text)

Max Activating Token Index: 472

Text #16

Max Range: 3.0641. Min Range: -3.0641

Max Act: 2.8891. Min Act: -0.1700

Data Index: 4464449 (Open Web Text)

Max Activating Token Index: 405

Text #17

Max Range: 3.0641. Min Range: -3.0641

Max Act: 2.8804. Min Act: -0.1700

Data Index: 6404302 (Open Web Text)

Max Activating Token Index: 747

Text #18

Max Range: 3.0641. Min Range: -3.0641

Max Act: 2.9130. Min Act: -0.1700

Data Index: 3572930 (Open Web Text)

Max Activating Token Index: 914

Text #19

Max Range: 3.0641. Min Range: -3.0641

Max Act: 2.8703. Min Act: -0.1700

Data Index: 7875277 (Open Web Text)

Max Activating Token Index: 48