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

Dataset: Open Web Text

Neuron 2641 in Layer 2

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: 1.4556. Min Range: -1.4556

Max Act: 1.4556. Min Act: -0.1700

Data Index: 6090494 (Open Web Text)

Max Activating Token Index: 430

Text #1

Max Range: 1.4556. Min Range: -1.4556

Max Act: 1.4123. Min Act: -0.1700

Data Index: 5401404 (Open Web Text)

Max Activating Token Index: 476

Text #2

Max Range: 1.4556. Min Range: -1.4556

Max Act: 1.4371. Min Act: -0.1700

Data Index: 884043 (Open Web Text)

Max Activating Token Index: 895

Text #3

Max Range: 1.4556. Min Range: -1.4556

Max Act: 1.4209. Min Act: -0.1700

Data Index: 438071 (Open Web Text)

Max Activating Token Index: 480

Text #4

Max Range: 1.4556. Min Range: -1.4556

Max Act: 1.3965. Min Act: -0.1700

Data Index: 2658155 (Open Web Text)

Max Activating Token Index: 150

Text #5

Max Range: 1.4556. Min Range: -1.4556

Max Act: 1.3978. Min Act: -0.1700

Data Index: 8209152 (Open Web Text)

Max Activating Token Index: 257

Text #6

Max Range: 1.4556. Min Range: -1.4556

Max Act: 1.3856. Min Act: -0.1700

Data Index: 935583 (Open Web Text)

Max Activating Token Index: 68

Text #7

Max Range: 1.4556. Min Range: -1.4556

Max Act: 1.3620. Min Act: -0.1700

Data Index: 5790683 (Open Web Text)

Max Activating Token Index: 152

Text #8

Max Range: 1.4556. Min Range: -1.4556

Max Act: 1.3808. Min Act: -0.1700

Data Index: 4612576 (Open Web Text)

Max Activating Token Index: 102

Text #9

Max Range: 1.4556. Min Range: -1.4556

Max Act: 1.3748. Min Act: -0.1699

Data Index: 2086533 (Open Web Text)

Max Activating Token Index: 188

Text #10

Max Range: 1.4556. Min Range: -1.4556

Max Act: 1.3790. Min Act: -0.1700

Data Index: 5509425 (Open Web Text)

Max Activating Token Index: 486

Text #11

Max Range: 1.4556. Min Range: -1.4556

Max Act: 1.3628. Min Act: -0.1700

Data Index: 5663848 (Open Web Text)

Max Activating Token Index: 880

Text #12

Max Range: 1.4556. Min Range: -1.4556

Max Act: 1.3637. Min Act: -0.1700

Data Index: 7530426 (Open Web Text)

Max Activating Token Index: 934

Text #13

Max Range: 1.4556. Min Range: -1.4556

Max Act: 1.3450. Min Act: -0.1700

Data Index: 387308 (Open Web Text)

Max Activating Token Index: 926

Text #14

Max Range: 1.4556. Min Range: -1.4556

Max Act: 1.3539. Min Act: -0.1700

Data Index: 3414133 (Open Web Text)

Max Activating Token Index: 954

Text #15

Max Range: 1.4556. Min Range: -1.4556

Max Act: 1.3378. Min Act: -0.1700

Data Index: 57629 (Open Web Text)

Max Activating Token Index: 463

Text #16

Max Range: 1.4556. Min Range: -1.4556

Max Act: 1.3467. Min Act: -0.1700

Data Index: 728763 (Open Web Text)

Max Activating Token Index: 377

Text #17

Max Range: 1.4556. Min Range: -1.4556

Max Act: 1.3433. Min Act: -0.1700

Data Index: 7501346 (Open Web Text)

Max Activating Token Index: 473

Text #18

Max Range: 1.4556. Min Range: -1.4556

Max Act: 1.3424. Min Act: -0.1700

Data Index: 6263944 (Open Web Text)

Max Activating Token Index: 981

Text #19

Max Range: 1.4556. Min Range: -1.4556

Max Act: 1.3534. Min Act: -0.1700

Data Index: 3113044 (Open Web Text)

Max Activating Token Index: 961