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

Dataset: Open Web Text

Neuron 2901 in Layer 0

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: 3.8968. Min Range: -3.8968

Max Act: 3.8968. Min Act: -0.1700

Data Index: 5667462 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 3.8968. Min Range: -3.8968

Max Act: 3.8439. Min Act: -0.1700

Data Index: 2408492 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 3.8968. Min Range: -3.8968

Max Act: 3.8285. Min Act: -0.1700

Data Index: 3652282 (Open Web Text)

Max Activating Token Index: 7

Text #3

Max Range: 3.8968. Min Range: -3.8968

Max Act: 3.7832. Min Act: -0.1700

Data Index: 4342053 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.8968. Min Range: -3.8968

Max Act: 3.7931. Min Act: -0.1700

Data Index: 3431049 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 3.8968. Min Range: -3.8968

Max Act: 3.7827. Min Act: -0.1700

Data Index: 733052 (Open Web Text)

Max Activating Token Index: 14

Text #6

Max Range: 3.8968. Min Range: -3.8968

Max Act: 3.7792. Min Act: -0.1700

Data Index: 7958751 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 3.8968. Min Range: -3.8968

Max Act: 3.7643. Min Act: -0.1700

Data Index: 579337 (Open Web Text)

Max Activating Token Index: 9

Text #8

Max Range: 3.8968. Min Range: -3.8968

Max Act: 3.7336. Min Act: -0.1700

Data Index: 7816525 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 3.8968. Min Range: -3.8968

Max Act: 3.7292. Min Act: -0.1700

Data Index: 3901998 (Open Web Text)

Max Activating Token Index: 16

Text #10

Max Range: 3.8968. Min Range: -3.8968

Max Act: 3.7203. Min Act: -0.1700

Data Index: 1520734 (Open Web Text)

Max Activating Token Index: 11

Text #11

Max Range: 3.8968. Min Range: -3.8968

Max Act: 3.6939. Min Act: -0.1700

Data Index: 4529489 (Open Web Text)

Max Activating Token Index: 19

Text #12

Max Range: 3.8968. Min Range: -3.8968

Max Act: 3.7051. Min Act: -0.1700

Data Index: 959312 (Open Web Text)

Max Activating Token Index: 11

Text #13

Max Range: 3.8968. Min Range: -3.8968

Max Act: 3.6939. Min Act: -0.1700

Data Index: 7348718 (Open Web Text)

Max Activating Token Index: 12

Text #14

Max Range: 3.8968. Min Range: -3.8968

Max Act: 3.7123. Min Act: -0.1700

Data Index: 385322 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 3.8968. Min Range: -3.8968

Max Act: 3.6950. Min Act: -0.1700

Data Index: 3922749 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 3.8968. Min Range: -3.8968

Max Act: 3.6734. Min Act: -0.1700

Data Index: 3208045 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 3.8968. Min Range: -3.8968

Max Act: 3.6506. Min Act: -0.1700

Data Index: 6371461 (Open Web Text)

Max Activating Token Index: 9

Text #18

Max Range: 3.8968. Min Range: -3.8968

Max Act: 3.6583. Min Act: -0.1700

Data Index: 7379676 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 3.8968. Min Range: -3.8968

Max Act: 3.6558. Min Act: -0.1700

Data Index: 1856500 (Open Web Text)

Max Activating Token Index: 11