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

Dataset: Open Web Text

Neuron 1474 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: 3.2417. Min Range: -3.2417

Max Act: 3.2417. Min Act: -0.1700

Data Index: 3375151 (Open Web Text)

Max Activating Token Index: 399

Text #1

Max Range: 3.2417. Min Range: -3.2417

Max Act: 3.0136. Min Act: -0.1700

Data Index: 8151811 (Open Web Text)

Max Activating Token Index: 898

Text #2

Max Range: 3.2417. Min Range: -3.2417

Max Act: 2.8604. Min Act: -0.1700

Data Index: 8720484 (Open Web Text)

Max Activating Token Index: 678

Text #3

Max Range: 3.2417. Min Range: -3.2417

Max Act: 2.8096. Min Act: -0.1700

Data Index: 2606397 (Open Web Text)

Max Activating Token Index: 704

Text #4

Max Range: 3.2417. Min Range: -3.2417

Max Act: 2.7586. Min Act: -0.1700

Data Index: 7307673 (Open Web Text)

Max Activating Token Index: 335

Text #5

Max Range: 3.2417. Min Range: -3.2417

Max Act: 2.7316. Min Act: -0.1700

Data Index: 7970008 (Open Web Text)

Max Activating Token Index: 797

Text #6

Max Range: 3.2417. Min Range: -3.2417

Max Act: 2.7588. Min Act: -0.1700

Data Index: 4523526 (Open Web Text)

Max Activating Token Index: 128

Text #7

Max Range: 3.2417. Min Range: -3.2417

Max Act: 2.7420. Min Act: -0.1700

Data Index: 5767304 (Open Web Text)

Max Activating Token Index: 205

Text #8

Max Range: 3.2417. Min Range: -3.2417

Max Act: 2.7330. Min Act: -0.1700

Data Index: 4005154 (Open Web Text)

Max Activating Token Index: 39

Text #9

Max Range: 3.2417. Min Range: -3.2417

Max Act: 2.7056. Min Act: -0.1700

Data Index: 2544100 (Open Web Text)

Max Activating Token Index: 536

Text #10

Max Range: 3.2417. Min Range: -3.2417

Max Act: 2.7141. Min Act: -0.1700

Data Index: 6103280 (Open Web Text)

Max Activating Token Index: 680

Text #11

Max Range: 3.2417. Min Range: -3.2417

Max Act: 2.7294. Min Act: -0.1700

Data Index: 6149409 (Open Web Text)

Max Activating Token Index: 898

Text #12

Max Range: 3.2417. Min Range: -3.2417

Max Act: 2.7140. Min Act: -0.1700

Data Index: 7788880 (Open Web Text)

Max Activating Token Index: 363

Text #13

Max Range: 3.2417. Min Range: -3.2417

Max Act: 2.7112. Min Act: -0.1700

Data Index: 1630644 (Open Web Text)

Max Activating Token Index: 191

Text #14

Max Range: 3.2417. Min Range: -3.2417

Max Act: 2.6970. Min Act: -0.1700

Data Index: 5217974 (Open Web Text)

Max Activating Token Index: 85

Text #15

Max Range: 3.2417. Min Range: -3.2417

Max Act: 2.6867. Min Act: -0.1700

Data Index: 2478427 (Open Web Text)

Max Activating Token Index: 69

Text #16

Max Range: 3.2417. Min Range: -3.2417

Max Act: 2.7113. Min Act: -0.1700

Data Index: 3636517 (Open Web Text)

Max Activating Token Index: 423

Text #17

Max Range: 3.2417. Min Range: -3.2417

Max Act: 2.7005. Min Act: -0.1700

Data Index: 5566612 (Open Web Text)

Max Activating Token Index: 468

Text #18

Max Range: 3.2417. Min Range: -3.2417

Max Act: 2.6831. Min Act: -0.1700

Data Index: 2976472 (Open Web Text)

Max Activating Token Index: 84

Text #19

Max Range: 3.2417. Min Range: -3.2417

Max Act: 2.6748. Min Act: -0.1700

Data Index: 5721575 (Open Web Text)

Max Activating Token Index: 450