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

Dataset: Open Web Text

Neuron 2115 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: 2.7203. Min Range: -2.7203

Max Act: 2.7203. Min Act: -0.1700

Data Index: 105562 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 2.7203. Min Range: -2.7203

Max Act: 2.6707. Min Act: -0.1700

Data Index: 831665 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 2.7203. Min Range: -2.7203

Max Act: 2.6575. Min Act: -0.1700

Data Index: 8218784 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 2.7203. Min Range: -2.7203

Max Act: 2.6575. Min Act: -0.1700

Data Index: 2104906 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 2.7203. Min Range: -2.7203

Max Act: 2.6275. Min Act: -0.1700

Data Index: 3422497 (Open Web Text)

Max Activating Token Index: 11

Text #5

Max Range: 2.7203. Min Range: -2.7203

Max Act: 2.6053. Min Act: -0.1700

Data Index: 7720385 (Open Web Text)

Max Activating Token Index: 19

Text #6

Max Range: 2.7203. Min Range: -2.7203

Max Act: 2.6078. Min Act: -0.1700

Data Index: 6565805 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 2.7203. Min Range: -2.7203

Max Act: 2.6151. Min Act: -0.1700

Data Index: 2481229 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 2.7203. Min Range: -2.7203

Max Act: 2.5751. Min Act: -0.1700

Data Index: 3916475 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 2.7203. Min Range: -2.7203

Max Act: 2.5768. Min Act: -0.1700

Data Index: 668121 (Open Web Text)

Max Activating Token Index: 14

Text #10

Max Range: 2.7203. Min Range: -2.7203

Max Act: 2.5790. Min Act: -0.1700

Data Index: 1288121 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 2.7203. Min Range: -2.7203

Max Act: 2.5639. Min Act: -0.1700

Data Index: 3116577 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 2.7203. Min Range: -2.7203

Max Act: 2.5548. Min Act: -0.1700

Data Index: 8587758 (Open Web Text)

Max Activating Token Index: 8

Text #13

Max Range: 2.7203. Min Range: -2.7203

Max Act: 2.5577. Min Act: -0.1700

Data Index: 4584464 (Open Web Text)

Max Activating Token Index: 8

Text #14

Max Range: 2.7203. Min Range: -2.7203

Max Act: 2.5444. Min Act: -0.1700

Data Index: 8707467 (Open Web Text)

Max Activating Token Index: 14

Text #15

Max Range: 2.7203. Min Range: -2.7203

Max Act: 2.5271. Min Act: -0.1700

Data Index: 5326416 (Open Web Text)

Max Activating Token Index: 17

Text #16

Max Range: 2.7203. Min Range: -2.7203

Max Act: 2.5228. Min Act: -0.1700

Data Index: 2277788 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 2.7203. Min Range: -2.7203

Max Act: 2.5319. Min Act: -0.1700

Data Index: 1834453 (Open Web Text)

Max Activating Token Index: 19

Text #18

Max Range: 2.7203. Min Range: -2.7203

Max Act: 2.5270. Min Act: -0.1700

Data Index: 1755000 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 2.7203. Min Range: -2.7203

Max Act: 2.5202. Min Act: -0.1700

Data Index: 1505599 (Open Web Text)

Max Activating Token Index: 5