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

Dataset: Open Web Text

Neuron 361 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: 3.3381. Min Range: -3.3381

Max Act: 3.3381. Min Act: -0.1700

Data Index: 4519822 (Open Web Text)

Max Activating Token Index: 8

Text #1

Max Range: 3.3381. Min Range: -3.3381

Max Act: 3.3046. Min Act: -0.1700

Data Index: 4790709 (Open Web Text)

Max Activating Token Index: 10

Text #2

Max Range: 3.3381. Min Range: -3.3381

Max Act: 3.2932. Min Act: -0.1700

Data Index: 4138775 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.3381. Min Range: -3.3381

Max Act: 3.2731. Min Act: -0.1700

Data Index: 1558174 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.3381. Min Range: -3.3381

Max Act: 3.2597. Min Act: -0.1700

Data Index: 5801099 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 3.3381. Min Range: -3.3381

Max Act: 3.2690. Min Act: -0.1700

Data Index: 7527194 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 3.3381. Min Range: -3.3381

Max Act: 3.2515. Min Act: -0.1700

Data Index: 1431249 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 3.3381. Min Range: -3.3381

Max Act: 3.2407. Min Act: -0.1700

Data Index: 4502935 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 3.3381. Min Range: -3.3381

Max Act: 3.2539. Min Act: -0.1700

Data Index: 2763508 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.3381. Min Range: -3.3381

Max Act: 3.2438. Min Act: -0.1700

Data Index: 4644138 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 3.3381. Min Range: -3.3381

Max Act: 3.2230. Min Act: -0.1700

Data Index: 7734405 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 3.3381. Min Range: -3.3381

Max Act: 3.2269. Min Act: -0.1700

Data Index: 1975155 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 3.3381. Min Range: -3.3381

Max Act: 3.2293. Min Act: -0.1700

Data Index: 7909602 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 3.3381. Min Range: -3.3381

Max Act: 3.2265. Min Act: -0.1700

Data Index: 5569267 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 3.3381. Min Range: -3.3381

Max Act: 3.2254. Min Act: -0.1700

Data Index: 6885424 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 3.3381. Min Range: -3.3381

Max Act: 3.2130. Min Act: -0.1700

Data Index: 4277515 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 3.3381. Min Range: -3.3381

Max Act: 3.2256. Min Act: -0.1700

Data Index: 5364145 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 3.3381. Min Range: -3.3381

Max Act: 3.2230. Min Act: -0.1700

Data Index: 5967970 (Open Web Text)

Max Activating Token Index: 8

Text #18

Max Range: 3.3381. Min Range: -3.3381

Max Act: 3.2168. Min Act: -0.1700

Data Index: 3594873 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 3.3381. Min Range: -3.3381

Max Act: 3.2181. Min Act: -0.1700

Data Index: 2190359 (Open Web Text)

Max Activating Token Index: 4