Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer

Dataset: Open Web Text

Neuron 3780 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')

Text #0

Max Range: 5.9520. Min Range: -5.9520

Max Act: 5.9520. Min Act: -0.1684

Data Index: 1288453 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 5.9520. Min Range: -5.9520

Max Act: 5.8270. Min Act: -0.1700

Data Index: 5006991 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 5.9520. Min Range: -5.9520

Max Act: 5.6707. Min Act: -0.1700

Data Index: 713837 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 5.9520. Min Range: -5.9520

Max Act: 5.7020. Min Act: -0.1700

Data Index: 1955550 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 5.9520. Min Range: -5.9520

Max Act: 5.6082. Min Act: -0.1700

Data Index: 578449 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 5.9520. Min Range: -5.9520

Max Act: 5.5770. Min Act: -0.1700

Data Index: 4963116 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 5.9520. Min Range: -5.9520

Max Act: 5.5770. Min Act: -0.1700

Data Index: 3235476 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 5.9520. Min Range: -5.9520

Max Act: 5.6082. Min Act: -0.1700

Data Index: 2879341 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 5.9520. Min Range: -5.9520

Max Act: 5.5770. Min Act: -0.1700

Data Index: 1046159 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 5.9520. Min Range: -5.9520

Max Act: 5.5457. Min Act: -0.1700

Data Index: 6757389 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 5.9520. Min Range: -5.9520

Max Act: 5.5457. Min Act: -0.1699

Data Index: 8006079 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 5.9520. Min Range: -5.9520

Max Act: 5.5457. Min Act: -0.1696

Data Index: 7290951 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 5.9520. Min Range: -5.9520

Max Act: 5.5457. Min Act: -0.1700

Data Index: 8482253 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 5.9520. Min Range: -5.9520

Max Act: 5.5145. Min Act: -0.1700

Data Index: 6727838 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 5.9520. Min Range: -5.9520

Max Act: 5.5145. Min Act: -0.1700

Data Index: 5101176 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 5.9520. Min Range: -5.9520

Max Act: 5.4832. Min Act: -0.1700

Data Index: 5145587 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 5.9520. Min Range: -5.9520

Max Act: 5.4832. Min Act: -0.1700

Data Index: 7567879 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 5.9520. Min Range: -5.9520

Max Act: 5.5145. Min Act: -0.1700

Data Index: 5319545 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 5.9520. Min Range: -5.9520

Max Act: 5.5145. Min Act: -0.1693

Data Index: 8031679 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 5.9520. Min Range: -5.9520

Max Act: 5.5145. Min Act: -0.1700

Data Index: 5043737 (Open Web Text)

Max Activating Token Index: 2