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

Dataset: Open Web Text

Neuron 1215 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: 3.4412. Min Range: -3.4412

Max Act: 3.4406. Min Act: -0.1700

Data Index: 3723515 (Open Web Text)

Max Activating Token Index: 999

Text #1

Max Range: 3.4412. Min Range: -3.4412

Max Act: 3.4412. Min Act: -0.1700

Data Index: 8025966 (Open Web Text)

Max Activating Token Index: 139

Text #2

Max Range: 3.4412. Min Range: -3.4412

Max Act: 3.3755. Min Act: -0.1700

Data Index: 1108159 (Open Web Text)

Max Activating Token Index: 672

Text #3

Max Range: 3.4412. Min Range: -3.4412

Max Act: 3.3666. Min Act: -0.1700

Data Index: 2141637 (Open Web Text)

Max Activating Token Index: 683

Text #4

Max Range: 3.4412. Min Range: -3.4412

Max Act: 3.3592. Min Act: -0.1700

Data Index: 7000487 (Open Web Text)

Max Activating Token Index: 351

Text #5

Max Range: 3.4412. Min Range: -3.4412

Max Act: 3.3361. Min Act: -0.1700

Data Index: 7438442 (Open Web Text)

Max Activating Token Index: 259

Text #6

Max Range: 3.4412. Min Range: -3.4412

Max Act: 3.3731. Min Act: -0.1700

Data Index: 6813131 (Open Web Text)

Max Activating Token Index: 111

Text #7

Max Range: 3.4412. Min Range: -3.4412

Max Act: 3.3167. Min Act: -0.1700

Data Index: 8514779 (Open Web Text)

Max Activating Token Index: 886

Text #8

Max Range: 3.4412. Min Range: -3.4412

Max Act: 3.3106. Min Act: -0.1700

Data Index: 2834179 (Open Web Text)

Max Activating Token Index: 540

Text #9

Max Range: 3.4412. Min Range: -3.4412

Max Act: 3.3004. Min Act: -0.1700

Data Index: 1032887 (Open Web Text)

Max Activating Token Index: 35

Text #10

Max Range: 3.4412. Min Range: -3.4412

Max Act: 3.3372. Min Act: -0.1700

Data Index: 2457248 (Open Web Text)

Max Activating Token Index: 418

Text #11

Max Range: 3.4412. Min Range: -3.4412

Max Act: 3.3429. Min Act: -0.1700

Data Index: 7147419 (Open Web Text)

Max Activating Token Index: 697

Text #12

Max Range: 3.4412. Min Range: -3.4412

Max Act: 3.3428. Min Act: -0.1700

Data Index: 1637909 (Open Web Text)

Max Activating Token Index: 11

Text #13

Max Range: 3.4412. Min Range: -3.4412

Max Act: 3.3506. Min Act: -0.1700

Data Index: 5610568 (Open Web Text)

Max Activating Token Index: 507

Text #14

Max Range: 3.4412. Min Range: -3.4412

Max Act: 3.3059. Min Act: -0.1700

Data Index: 4748467 (Open Web Text)

Max Activating Token Index: 457

Text #15

Max Range: 3.4412. Min Range: -3.4412

Max Act: 3.2840. Min Act: -0.1700

Data Index: 4969796 (Open Web Text)

Max Activating Token Index: 140

Text #16

Max Range: 3.4412. Min Range: -3.4412

Max Act: 3.3169. Min Act: -0.1700

Data Index: 2100360 (Open Web Text)

Max Activating Token Index: 481

Text #17

Max Range: 3.4412. Min Range: -3.4412

Max Act: 3.3394. Min Act: -0.1700

Data Index: 5242965 (Open Web Text)

Max Activating Token Index: 805

Text #18

Max Range: 3.4412. Min Range: -3.4412

Max Act: 3.3050. Min Act: -0.1700

Data Index: 909745 (Open Web Text)

Max Activating Token Index: 30

Text #19

Max Range: 3.4412. Min Range: -3.4412

Max Act: 3.2953. Min Act: -0.1700

Data Index: 7883199 (Open Web Text)

Max Activating Token Index: 797