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

Dataset: Open Web Text

Neuron 2626 in Layer 1

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: 4.2846. Min Range: -4.2846

Max Act: 4.2846. Min Act: -0.1700

Data Index: 3125472 (Open Web Text)

Max Activating Token Index: 18

Text #1

Max Range: 4.2846. Min Range: -4.2846

Max Act: 4.2356. Min Act: -0.1700

Data Index: 7788992 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 4.2846. Min Range: -4.2846

Max Act: 4.2475. Min Act: -0.1700

Data Index: 7583825 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 4.2846. Min Range: -4.2846

Max Act: 4.1754. Min Act: -0.1700

Data Index: 4915450 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 4.2846. Min Range: -4.2846

Max Act: 4.1643. Min Act: -0.1700

Data Index: 2366259 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 4.2846. Min Range: -4.2846

Max Act: 4.1643. Min Act: -0.1700

Data Index: 7949743 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 4.2846. Min Range: -4.2846

Max Act: 4.1643. Min Act: -0.1700

Data Index: 3176888 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 4.2846. Min Range: -4.2846

Max Act: 4.1643. Min Act: -0.1700

Data Index: 6207968 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 4.2846. Min Range: -4.2846

Max Act: 4.1497. Min Act: -0.1700

Data Index: 778202 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 4.2846. Min Range: -4.2846

Max Act: 4.1551. Min Act: -0.1700

Data Index: 660571 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 4.2846. Min Range: -4.2846

Max Act: 4.1334. Min Act: -0.1700

Data Index: 4270655 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 4.2846. Min Range: -4.2846

Max Act: 4.1195. Min Act: -0.1700

Data Index: 3004624 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 4.2846. Min Range: -4.2846

Max Act: 4.1348. Min Act: -0.1700

Data Index: 2570636 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 4.2846. Min Range: -4.2846

Max Act: 4.1248. Min Act: -0.1700

Data Index: 3092675 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 4.2846. Min Range: -4.2846

Max Act: 4.1192. Min Act: -0.1700

Data Index: 1503485 (Open Web Text)

Max Activating Token Index: 550

Text #15

Max Range: 4.2846. Min Range: -4.2846

Max Act: 4.1099. Min Act: -0.1700

Data Index: 3052476 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 4.2846. Min Range: -4.2846

Max Act: 4.1344. Min Act: -0.1700

Data Index: 5045629 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 4.2846. Min Range: -4.2846

Max Act: 4.0807. Min Act: -0.1700

Data Index: 7577008 (Open Web Text)

Max Activating Token Index: 9

Text #18

Max Range: 4.2846. Min Range: -4.2846

Max Act: 4.0802. Min Act: -0.1700

Data Index: 6748973 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 4.2846. Min Range: -4.2846

Max Act: 4.0964. Min Act: -0.1700

Data Index: 1354091 (Open Web Text)

Max Activating Token Index: 4