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

Dataset: Open Web Text

Neuron 1211 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: 4.9189. Min Range: -4.9189

Max Act: 4.9065. Min Act: -0.1700

Data Index: 1613398 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 4.9189. Min Range: -4.9189

Max Act: 4.9189. Min Act: -0.1700

Data Index: 3663167 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 4.9189. Min Range: -4.9189

Max Act: 4.9041. Min Act: -0.1700

Data Index: 5170597 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 4.9189. Min Range: -4.9189

Max Act: 4.8413. Min Act: -0.1700

Data Index: 4906789 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 4.9189. Min Range: -4.9189

Max Act: 4.8487. Min Act: -0.1700

Data Index: 7735789 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 4.9189. Min Range: -4.9189

Max Act: 4.8003. Min Act: -0.1700

Data Index: 2899524 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 4.9189. Min Range: -4.9189

Max Act: 4.7953. Min Act: -0.1700

Data Index: 8332348 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 4.9189. Min Range: -4.9189

Max Act: 4.7570. Min Act: -0.1700

Data Index: 4537895 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 4.9189. Min Range: -4.9189

Max Act: 4.7433. Min Act: -0.1700

Data Index: 6831571 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 4.9189. Min Range: -4.9189

Max Act: 4.7628. Min Act: -0.1700

Data Index: 6447671 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 4.9189. Min Range: -4.9189

Max Act: 4.7548. Min Act: -0.1700

Data Index: 4681698 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 4.9189. Min Range: -4.9189

Max Act: 4.7619. Min Act: -0.1700

Data Index: 5474961 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 4.9189. Min Range: -4.9189

Max Act: 4.7418. Min Act: -0.1700

Data Index: 3355523 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 4.9189. Min Range: -4.9189

Max Act: 4.7373. Min Act: -0.1700

Data Index: 1587910 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 4.9189. Min Range: -4.9189

Max Act: 4.7493. Min Act: -0.1700

Data Index: 8157735 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 4.9189. Min Range: -4.9189

Max Act: 4.7498. Min Act: -0.1700

Data Index: 3529101 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 4.9189. Min Range: -4.9189

Max Act: 4.7336. Min Act: -0.1700

Data Index: 4385124 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 4.9189. Min Range: -4.9189

Max Act: 4.7282. Min Act: -0.1700

Data Index: 3389829 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 4.9189. Min Range: -4.9189

Max Act: 4.7066. Min Act: -0.1700

Data Index: 5926979 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 4.9189. Min Range: -4.9189

Max Act: 4.7177. Min Act: -0.1700

Data Index: 1970328 (Open Web Text)

Max Activating Token Index: 4