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

Dataset: Open Web Text

Neuron 645 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: 4.6221. Min Range: -4.6221

Max Act: 4.6221. Min Act: -0.1700

Data Index: 7948011 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 4.6221. Min Range: -4.6221

Max Act: 4.5322. Min Act: -0.1700

Data Index: 1498875 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 4.6221. Min Range: -4.6221

Max Act: 4.4704. Min Act: -0.1700

Data Index: 20731 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 4.6221. Min Range: -4.6221

Max Act: 4.4671. Min Act: -0.1700

Data Index: 3496403 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 4.6221. Min Range: -4.6221

Max Act: 4.4518. Min Act: -0.1700

Data Index: 7826138 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 4.6221. Min Range: -4.6221

Max Act: 4.4150. Min Act: -0.1700

Data Index: 6084662 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 4.6221. Min Range: -4.6221

Max Act: 4.4276. Min Act: -0.1700

Data Index: 4414646 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 4.6221. Min Range: -4.6221

Max Act: 4.4197. Min Act: -0.1700

Data Index: 4032824 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 4.6221. Min Range: -4.6221

Max Act: 4.3746. Min Act: -0.1700

Data Index: 1138694 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 4.6221. Min Range: -4.6221

Max Act: 4.3816. Min Act: -0.1700

Data Index: 5317519 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 4.6221. Min Range: -4.6221

Max Act: 4.4039. Min Act: -0.1700

Data Index: 184517 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 4.6221. Min Range: -4.6221

Max Act: 4.3861. Min Act: -0.1700

Data Index: 1579109 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 4.6221. Min Range: -4.6221

Max Act: 4.3886. Min Act: -0.1700

Data Index: 7052597 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 4.6221. Min Range: -4.6221

Max Act: 4.3915. Min Act: -0.1700

Data Index: 2914040 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 4.6221. Min Range: -4.6221

Max Act: 4.3836. Min Act: -0.1700

Data Index: 7551796 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 4.6221. Min Range: -4.6221

Max Act: 4.3493. Min Act: -0.1700

Data Index: 7848985 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 4.6221. Min Range: -4.6221

Max Act: 4.3593. Min Act: -0.1700

Data Index: 4265642 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 4.6221. Min Range: -4.6221

Max Act: 4.3456. Min Act: -0.1700

Data Index: 7191473 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 4.6221. Min Range: -4.6221

Max Act: 4.3551. Min Act: -0.1700

Data Index: 6275847 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 4.6221. Min Range: -4.6221

Max Act: 4.3566. Min Act: -0.1700

Data Index: 5891289 (Open Web Text)

Max Activating Token Index: 4