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

Dataset: Open Web Text

Neuron 481 in Layer 4

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: 4.1112. Min Range: -4.1112

Max Act: 4.1112. Min Act: -0.1700

Data Index: 4007530 (Open Web Text)

Max Activating Token Index: 546

Text #1

Max Range: 4.1112. Min Range: -4.1112

Max Act: 4.0656. Min Act: -0.1700

Data Index: 5459753 (Open Web Text)

Max Activating Token Index: 589

Text #2

Max Range: 4.1112. Min Range: -4.1112

Max Act: 4.0494. Min Act: -0.1700

Data Index: 6996709 (Open Web Text)

Max Activating Token Index: 298

Text #3

Max Range: 4.1112. Min Range: -4.1112

Max Act: 4.0440. Min Act: -0.1700

Data Index: 2903789 (Open Web Text)

Max Activating Token Index: 430

Text #4

Max Range: 4.1112. Min Range: -4.1112

Max Act: 4.0388. Min Act: -0.1700

Data Index: 2078310 (Open Web Text)

Max Activating Token Index: 692

Text #5

Max Range: 4.1112. Min Range: -4.1112

Max Act: 4.0343. Min Act: -0.1700

Data Index: 6123118 (Open Web Text)

Max Activating Token Index: 916

Text #6

Max Range: 4.1112. Min Range: -4.1112

Max Act: 4.0086. Min Act: -0.1700

Data Index: 3939261 (Open Web Text)

Max Activating Token Index: 528

Text #7

Max Range: 4.1112. Min Range: -4.1112

Max Act: 4.0065. Min Act: -0.1700

Data Index: 3894092 (Open Web Text)

Max Activating Token Index: 498

Text #8

Max Range: 4.1112. Min Range: -4.1112

Max Act: 3.9793. Min Act: -0.1700

Data Index: 8439970 (Open Web Text)

Max Activating Token Index: 160

Text #9

Max Range: 4.1112. Min Range: -4.1112

Max Act: 4.0027. Min Act: -0.1700

Data Index: 3599616 (Open Web Text)

Max Activating Token Index: 469

Text #10

Max Range: 4.1112. Min Range: -4.1112

Max Act: 3.9898. Min Act: -0.1700

Data Index: 8325252 (Open Web Text)

Max Activating Token Index: 646

Text #11

Max Range: 4.1112. Min Range: -4.1112

Max Act: 3.9439. Min Act: -0.1700

Data Index: 1241908 (Open Web Text)

Max Activating Token Index: 587

Text #12

Max Range: 4.1112. Min Range: -4.1112

Max Act: 3.9600. Min Act: -0.1700

Data Index: 1428185 (Open Web Text)

Max Activating Token Index: 179

Text #13

Max Range: 4.1112. Min Range: -4.1112

Max Act: 3.9685. Min Act: -0.1700

Data Index: 4941098 (Open Web Text)

Max Activating Token Index: 686

Text #14

Max Range: 4.1112. Min Range: -4.1112

Max Act: 3.9699. Min Act: -0.1700

Data Index: 6674544 (Open Web Text)

Max Activating Token Index: 445

Text #15

Max Range: 4.1112. Min Range: -4.1112

Max Act: 3.9365. Min Act: -0.1700

Data Index: 1902939 (Open Web Text)

Max Activating Token Index: 779

Text #16

Max Range: 4.1112. Min Range: -4.1112

Max Act: 3.9306. Min Act: -0.1700

Data Index: 3971031 (Open Web Text)

Max Activating Token Index: 928

Text #17

Max Range: 4.1112. Min Range: -4.1112

Max Act: 3.9370. Min Act: -0.1700

Data Index: 442261 (Open Web Text)

Max Activating Token Index: 631

Text #18

Max Range: 4.1112. Min Range: -4.1112

Max Act: 3.9373. Min Act: -0.1700

Data Index: 2474097 (Open Web Text)

Max Activating Token Index: 720

Text #19

Max Range: 4.1112. Min Range: -4.1112

Max Act: 3.9359. Min Act: -0.1700

Data Index: 6837596 (Open Web Text)

Max Activating Token Index: 64