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

Dataset: Open Web Text

Neuron 1949 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: 2.8124. Min Range: -2.8124

Max Act: 2.8124. Min Act: -0.1700

Data Index: 6256883 (Open Web Text)

Max Activating Token Index: 8

Text #1

Max Range: 2.8124. Min Range: -2.8124

Max Act: 2.7490. Min Act: -0.1700

Data Index: 6308318 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 2.8124. Min Range: -2.8124

Max Act: 2.7055. Min Act: -0.1700

Data Index: 8655110 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 2.8124. Min Range: -2.8124

Max Act: 2.7066. Min Act: -0.1700

Data Index: 1224084 (Open Web Text)

Max Activating Token Index: 51

Text #4

Max Range: 2.8124. Min Range: -2.8124

Max Act: 2.6992. Min Act: -0.1700

Data Index: 2666534 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 2.8124. Min Range: -2.8124

Max Act: 2.6835. Min Act: -0.1700

Data Index: 2669431 (Open Web Text)

Max Activating Token Index: 16

Text #6

Max Range: 2.8124. Min Range: -2.8124

Max Act: 2.6803. Min Act: -0.1700

Data Index: 6737290 (Open Web Text)

Max Activating Token Index: 16

Text #7

Max Range: 2.8124. Min Range: -2.8124

Max Act: 2.6800. Min Act: -0.1700

Data Index: 4402862 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 2.8124. Min Range: -2.8124

Max Act: 2.6557. Min Act: -0.1700

Data Index: 7639284 (Open Web Text)

Max Activating Token Index: 30

Text #9

Max Range: 2.8124. Min Range: -2.8124

Max Act: 2.6585. Min Act: -0.1700

Data Index: 8735140 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 2.8124. Min Range: -2.8124

Max Act: 2.6558. Min Act: -0.1700

Data Index: 7632407 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 2.8124. Min Range: -2.8124

Max Act: 2.6646. Min Act: -0.1700

Data Index: 4421656 (Open Web Text)

Max Activating Token Index: 9

Text #12

Max Range: 2.8124. Min Range: -2.8124

Max Act: 2.6391. Min Act: -0.1700

Data Index: 5852171 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 2.8124. Min Range: -2.8124

Max Act: 2.6520. Min Act: -0.1700

Data Index: 2327028 (Open Web Text)

Max Activating Token Index: 21

Text #14

Max Range: 2.8124. Min Range: -2.8124

Max Act: 2.6377. Min Act: -0.1700

Data Index: 5732090 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 2.8124. Min Range: -2.8124

Max Act: 2.6238. Min Act: -0.1700

Data Index: 3552284 (Open Web Text)

Max Activating Token Index: 26

Text #16

Max Range: 2.8124. Min Range: -2.8124

Max Act: 2.6302. Min Act: -0.1700

Data Index: 7465601 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 2.8124. Min Range: -2.8124

Max Act: 2.6247. Min Act: -0.1700

Data Index: 7256926 (Open Web Text)

Max Activating Token Index: 311

Text #18

Max Range: 2.8124. Min Range: -2.8124

Max Act: 2.6373. Min Act: -0.1700

Data Index: 2360833 (Open Web Text)

Max Activating Token Index: 630

Text #19

Max Range: 2.8124. Min Range: -2.8124

Max Act: 2.6270. Min Act: -0.1700

Data Index: 6335978 (Open Web Text)

Max Activating Token Index: 5