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

Dataset: Open Web Text

Neuron 1931 in Layer 1

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: 1.9455. Min Range: -1.9455

Max Act: 1.9455. Min Act: -0.1700

Data Index: 8469419 (Open Web Text)

Max Activating Token Index: 823

Text #1

Max Range: 1.9455. Min Range: -1.9455

Max Act: 1.9253. Min Act: -0.1700

Data Index: 6781523 (Open Web Text)

Max Activating Token Index: 688

Text #2

Max Range: 1.9455. Min Range: -1.9455

Max Act: 1.8940. Min Act: -0.1700

Data Index: 6957479 (Open Web Text)

Max Activating Token Index: 12

Text #3

Max Range: 1.9455. Min Range: -1.9455

Max Act: 1.8888. Min Act: -0.1700

Data Index: 7646714 (Open Web Text)

Max Activating Token Index: 56

Text #4

Max Range: 1.9455. Min Range: -1.9455

Max Act: 1.8790. Min Act: -0.1700

Data Index: 5820104 (Open Web Text)

Max Activating Token Index: 706

Text #5

Max Range: 1.9455. Min Range: -1.9455

Max Act: 1.8645. Min Act: -0.1700

Data Index: 182819 (Open Web Text)

Max Activating Token Index: 49

Text #6

Max Range: 1.9455. Min Range: -1.9455

Max Act: 1.8627. Min Act: -0.1700

Data Index: 3466326 (Open Web Text)

Max Activating Token Index: 815

Text #7

Max Range: 1.9455. Min Range: -1.9455

Max Act: 1.8698. Min Act: -0.1700

Data Index: 5654397 (Open Web Text)

Max Activating Token Index: 79

Text #8

Max Range: 1.9455. Min Range: -1.9455

Max Act: 1.8580. Min Act: -0.1700

Data Index: 2713376 (Open Web Text)

Max Activating Token Index: 550

Text #9

Max Range: 1.9455. Min Range: -1.9455

Max Act: 1.8573. Min Act: -0.1700

Data Index: 5626132 (Open Web Text)

Max Activating Token Index: 444

Text #10

Max Range: 1.9455. Min Range: -1.9455

Max Act: 1.8581. Min Act: -0.1700

Data Index: 6310911 (Open Web Text)

Max Activating Token Index: 488

Text #11

Max Range: 1.9455. Min Range: -1.9455

Max Act: 1.8444. Min Act: -0.1700

Data Index: 8233508 (Open Web Text)

Max Activating Token Index: 688

Text #12

Max Range: 1.9455. Min Range: -1.9455

Max Act: 1.8380. Min Act: -0.1700

Data Index: 5605316 (Open Web Text)

Max Activating Token Index: 834

Text #13

Max Range: 1.9455. Min Range: -1.9455

Max Act: 1.8346. Min Act: -0.1700

Data Index: 1128987 (Open Web Text)

Max Activating Token Index: 604

Text #14

Max Range: 1.9455. Min Range: -1.9455

Max Act: 1.8465. Min Act: -0.1700

Data Index: 5906613 (Open Web Text)

Max Activating Token Index: 765

Text #15

Max Range: 1.9455. Min Range: -1.9455

Max Act: 1.8522. Min Act: -0.1700

Data Index: 1593352 (Open Web Text)

Max Activating Token Index: 256

Text #16

Max Range: 1.9455. Min Range: -1.9455

Max Act: 1.8397. Min Act: -0.1700

Data Index: 6957478 (Open Web Text)

Max Activating Token Index: 542

Text #17

Max Range: 1.9455. Min Range: -1.9455

Max Act: 1.8475. Min Act: -0.1700

Data Index: 2708998 (Open Web Text)

Max Activating Token Index: 400

Text #18

Max Range: 1.9455. Min Range: -1.9455

Max Act: 1.8373. Min Act: -0.1700

Data Index: 4650053 (Open Web Text)

Max Activating Token Index: 530

Text #19

Max Range: 1.9455. Min Range: -1.9455

Max Act: 1.8347. Min Act: -0.1700

Data Index: 4814801 (Open Web Text)

Max Activating Token Index: 543