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

Dataset: Open Web Text

Neuron 1069 in Layer 2

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: 3.0299. Min Range: -3.0299

Max Act: 3.0299. Min Act: -0.1700

Data Index: 8770714 (Open Web Text)

Max Activating Token Index: 84

Text #1

Max Range: 3.0299. Min Range: -3.0299

Max Act: 2.8907. Min Act: -0.1700

Data Index: 6992530 (Open Web Text)

Max Activating Token Index: 757

Text #2

Max Range: 3.0299. Min Range: -3.0299

Max Act: 2.8055. Min Act: -0.1700

Data Index: 1841677 (Open Web Text)

Max Activating Token Index: 326

Text #3

Max Range: 3.0299. Min Range: -3.0299

Max Act: 2.8312. Min Act: -0.1700

Data Index: 5333911 (Open Web Text)

Max Activating Token Index: 548

Text #4

Max Range: 3.0299. Min Range: -3.0299

Max Act: 2.8092. Min Act: -0.1700

Data Index: 2791810 (Open Web Text)

Max Activating Token Index: 47

Text #5

Max Range: 3.0299. Min Range: -3.0299

Max Act: 2.7556. Min Act: -0.1700

Data Index: 6449703 (Open Web Text)

Max Activating Token Index: 9

Text #6

Max Range: 3.0299. Min Range: -3.0299

Max Act: 2.7824. Min Act: -0.1700

Data Index: 1697294 (Open Web Text)

Max Activating Token Index: 922

Text #7

Max Range: 3.0299. Min Range: -3.0299

Max Act: 2.7723. Min Act: -0.1700

Data Index: 2875351 (Open Web Text)

Max Activating Token Index: 57

Text #8

Max Range: 3.0299. Min Range: -3.0299

Max Act: 2.7316. Min Act: -0.1700

Data Index: 1220482 (Open Web Text)

Max Activating Token Index: 8

Text #9

Max Range: 3.0299. Min Range: -3.0299

Max Act: 2.7395. Min Act: -0.1700

Data Index: 5785835 (Open Web Text)

Max Activating Token Index: 118

Text #10

Max Range: 3.0299. Min Range: -3.0299

Max Act: 2.7167. Min Act: -0.1700

Data Index: 5641457 (Open Web Text)

Max Activating Token Index: 242

Text #11

Max Range: 3.0299. Min Range: -3.0299

Max Act: 2.6902. Min Act: -0.1700

Data Index: 1246582 (Open Web Text)

Max Activating Token Index: 111

Text #12

Max Range: 3.0299. Min Range: -3.0299

Max Act: 2.6869. Min Act: -0.1700

Data Index: 406909 (Open Web Text)

Max Activating Token Index: 882

Text #13

Max Range: 3.0299. Min Range: -3.0299

Max Act: 2.6741. Min Act: -0.1700

Data Index: 4193835 (Open Web Text)

Max Activating Token Index: 555

Text #14

Max Range: 3.0299. Min Range: -3.0299

Max Act: 2.6671. Min Act: -0.1700

Data Index: 5485007 (Open Web Text)

Max Activating Token Index: 863

Text #15

Max Range: 3.0299. Min Range: -3.0299

Max Act: 2.6953. Min Act: -0.1700

Data Index: 7593870 (Open Web Text)

Max Activating Token Index: 168

Text #16

Max Range: 3.0299. Min Range: -3.0299

Max Act: 2.6313. Min Act: -0.1700

Data Index: 5042661 (Open Web Text)

Max Activating Token Index: 619

Text #17

Max Range: 3.0299. Min Range: -3.0299

Max Act: 2.6331. Min Act: -0.1700

Data Index: 4061733 (Open Web Text)

Max Activating Token Index: 631

Text #18

Max Range: 3.0299. Min Range: -3.0299

Max Act: 2.6347. Min Act: -0.1700

Data Index: 4873798 (Open Web Text)

Max Activating Token Index: 270

Text #19

Max Range: 3.0299. Min Range: -3.0299

Max Act: 2.6260. Min Act: -0.1700

Data Index: 6774910 (Open Web Text)

Max Activating Token Index: 28