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

Dataset: Open Web Text

Neuron 78 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: 1.4068. Min Range: -1.4068

Max Act: 1.4068. Min Act: -0.1700

Data Index: 3586208 (Open Web Text)

Max Activating Token Index: 18

Text #1

Max Range: 1.4068. Min Range: -1.4068

Max Act: 1.3749. Min Act: -0.1700

Data Index: 5986677 (Open Web Text)

Max Activating Token Index: 91

Text #2

Max Range: 1.4068. Min Range: -1.4068

Max Act: 1.3651. Min Act: -0.1700

Data Index: 4777064 (Open Web Text)

Max Activating Token Index: 70

Text #3

Max Range: 1.4068. Min Range: -1.4068

Max Act: 1.3580. Min Act: -0.1697

Data Index: 552463 (Open Web Text)

Max Activating Token Index: 756

Text #4

Max Range: 1.4068. Min Range: -1.4068

Max Act: 1.3588. Min Act: -0.1699

Data Index: 5882867 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 1.4068. Min Range: -1.4068

Max Act: 1.3531. Min Act: -0.1700

Data Index: 3042926 (Open Web Text)

Max Activating Token Index: 8

Text #6

Max Range: 1.4068. Min Range: -1.4068

Max Act: 1.3443. Min Act: -0.1700

Data Index: 1062248 (Open Web Text)

Max Activating Token Index: 14

Text #7

Max Range: 1.4068. Min Range: -1.4068

Max Act: 1.3510. Min Act: -0.1700

Data Index: 2373123 (Open Web Text)

Max Activating Token Index: 42

Text #8

Max Range: 1.4068. Min Range: -1.4068

Max Act: 1.3508. Min Act: -0.1700

Data Index: 6812203 (Open Web Text)

Max Activating Token Index: 14

Text #9

Max Range: 1.4068. Min Range: -1.4068

Max Act: 1.3382. Min Act: -0.1700

Data Index: 338635 (Open Web Text)

Max Activating Token Index: 25

Text #10

Max Range: 1.4068. Min Range: -1.4068

Max Act: 1.3399. Min Act: -0.1700

Data Index: 2723553 (Open Web Text)

Max Activating Token Index: 10

Text #11

Max Range: 1.4068. Min Range: -1.4068

Max Act: 1.3402. Min Act: -0.1700

Data Index: 4938186 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 1.4068. Min Range: -1.4068

Max Act: 1.3461. Min Act: -0.1700

Data Index: 6346319 (Open Web Text)

Max Activating Token Index: 36

Text #13

Max Range: 1.4068. Min Range: -1.4068

Max Act: 1.3465. Min Act: -0.1699

Data Index: 5874424 (Open Web Text)

Max Activating Token Index: 28

Text #14

Max Range: 1.4068. Min Range: -1.4068

Max Act: 1.3473. Min Act: -0.1700

Data Index: 1004439 (Open Web Text)

Max Activating Token Index: 177

Text #15

Max Range: 1.4068. Min Range: -1.4068

Max Act: 1.3427. Min Act: -0.1689

Data Index: 58063 (Open Web Text)

Max Activating Token Index: 65

Text #16

Max Range: 1.4068. Min Range: -1.4068

Max Act: 1.3481. Min Act: -0.1697

Data Index: 1975523 (Open Web Text)

Max Activating Token Index: 269

Text #17

Max Range: 1.4068. Min Range: -1.4068

Max Act: 1.3449. Min Act: -0.1700

Data Index: 5217923 (Open Web Text)

Max Activating Token Index: 651

Text #18

Max Range: 1.4068. Min Range: -1.4068

Max Act: 1.3446. Min Act: -0.1699

Data Index: 4973515 (Open Web Text)

Max Activating Token Index: 33

Text #19

Max Range: 1.4068. Min Range: -1.4068

Max Act: 1.3329. Min Act: -0.1700

Data Index: 4343489 (Open Web Text)

Max Activating Token Index: 723