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

Dataset: Open Web Text

Neuron 2584 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: 3.5813. Min Range: -3.5813

Max Act: 3.5813. Min Act: -0.1700

Data Index: 5035489 (Open Web Text)

Max Activating Token Index: 13

Text #1

Max Range: 3.5813. Min Range: -3.5813

Max Act: 3.5296. Min Act: -0.1700

Data Index: 316681 (Open Web Text)

Max Activating Token Index: 651

Text #2

Max Range: 3.5813. Min Range: -3.5813

Max Act: 3.4876. Min Act: -0.1700

Data Index: 3116403 (Open Web Text)

Max Activating Token Index: 939

Text #3

Max Range: 3.5813. Min Range: -3.5813

Max Act: 3.4777. Min Act: -0.1700

Data Index: 8465138 (Open Web Text)

Max Activating Token Index: 9

Text #4

Max Range: 3.5813. Min Range: -3.5813

Max Act: 3.4339. Min Act: -0.1700

Data Index: 5131483 (Open Web Text)

Max Activating Token Index: 499

Text #5

Max Range: 3.5813. Min Range: -3.5813

Max Act: 3.4485. Min Act: -0.1700

Data Index: 8125205 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 3.5813. Min Range: -3.5813

Max Act: 3.4331. Min Act: -0.1700

Data Index: 4545000 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 3.5813. Min Range: -3.5813

Max Act: 3.4359. Min Act: -0.1700

Data Index: 3713840 (Open Web Text)

Max Activating Token Index: 17

Text #8

Max Range: 3.5813. Min Range: -3.5813

Max Act: 3.4002. Min Act: -0.1700

Data Index: 4802424 (Open Web Text)

Max Activating Token Index: 540

Text #9

Max Range: 3.5813. Min Range: -3.5813

Max Act: 3.3650. Min Act: -0.1700

Data Index: 5165824 (Open Web Text)

Max Activating Token Index: 1010

Text #10

Max Range: 3.5813. Min Range: -3.5813

Max Act: 3.3960. Min Act: -0.1700

Data Index: 1638211 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 3.5813. Min Range: -3.5813

Max Act: 3.4003. Min Act: -0.1700

Data Index: 4610992 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 3.5813. Min Range: -3.5813

Max Act: 3.4061. Min Act: -0.1700

Data Index: 415622 (Open Web Text)

Max Activating Token Index: 33

Text #13

Max Range: 3.5813. Min Range: -3.5813

Max Act: 3.3841. Min Act: -0.1700

Data Index: 1932337 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 3.5813. Min Range: -3.5813

Max Act: 3.4120. Min Act: -0.1700

Data Index: 4406236 (Open Web Text)

Max Activating Token Index: 888

Text #15

Max Range: 3.5813. Min Range: -3.5813

Max Act: 3.3987. Min Act: -0.1700

Data Index: 3285394 (Open Web Text)

Max Activating Token Index: 328

Text #16

Max Range: 3.5813. Min Range: -3.5813

Max Act: 3.3877. Min Act: -0.1700

Data Index: 6930290 (Open Web Text)

Max Activating Token Index: 532

Text #17

Max Range: 3.5813. Min Range: -3.5813

Max Act: 3.3793. Min Act: -0.1700

Data Index: 6866120 (Open Web Text)

Max Activating Token Index: 963

Text #18

Max Range: 3.5813. Min Range: -3.5813

Max Act: 3.3681. Min Act: -0.1700

Data Index: 2714764 (Open Web Text)

Max Activating Token Index: 905

Text #19

Max Range: 3.5813. Min Range: -3.5813

Max Act: 3.3643. Min Act: -0.1700

Data Index: 5567899 (Open Web Text)

Max Activating Token Index: 14