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

Dataset: Open Web Text

Neuron 1912 in Layer 5

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: 3.8516. Min Range: -3.8516

Max Act: 3.8516. Min Act: -0.1700

Data Index: 2979321 (Open Web Text)

Max Activating Token Index: 866

Text #1

Max Range: 3.8516. Min Range: -3.8516

Max Act: 3.8408. Min Act: -0.1700

Data Index: 5660459 (Open Web Text)

Max Activating Token Index: 442

Text #2

Max Range: 3.8516. Min Range: -3.8516

Max Act: 3.8192. Min Act: -0.1700

Data Index: 5617082 (Open Web Text)

Max Activating Token Index: 149

Text #3

Max Range: 3.8516. Min Range: -3.8516

Max Act: 3.8341. Min Act: -0.1700

Data Index: 1185168 (Open Web Text)

Max Activating Token Index: 488

Text #4

Max Range: 3.8516. Min Range: -3.8516

Max Act: 3.8260. Min Act: -0.1700

Data Index: 4236069 (Open Web Text)

Max Activating Token Index: 188

Text #5

Max Range: 3.8516. Min Range: -3.8516

Max Act: 3.8163. Min Act: -0.1700

Data Index: 1159750 (Open Web Text)

Max Activating Token Index: 492

Text #6

Max Range: 3.8516. Min Range: -3.8516

Max Act: 3.7618. Min Act: -0.1700

Data Index: 543401 (Open Web Text)

Max Activating Token Index: 612

Text #7

Max Range: 3.8516. Min Range: -3.8516

Max Act: 3.7637. Min Act: -0.1700

Data Index: 8366103 (Open Web Text)

Max Activating Token Index: 752

Text #8

Max Range: 3.8516. Min Range: -3.8516

Max Act: 3.7419. Min Act: -0.1700

Data Index: 1210494 (Open Web Text)

Max Activating Token Index: 529

Text #9

Max Range: 3.8516. Min Range: -3.8516

Max Act: 3.7325. Min Act: -0.1700

Data Index: 7672869 (Open Web Text)

Max Activating Token Index: 733

Text #10

Max Range: 3.8516. Min Range: -3.8516

Max Act: 3.7348. Min Act: -0.1700

Data Index: 2932259 (Open Web Text)

Max Activating Token Index: 104

Text #11

Max Range: 3.8516. Min Range: -3.8516

Max Act: 3.7351. Min Act: -0.1700

Data Index: 1268258 (Open Web Text)

Max Activating Token Index: 554

Text #12

Max Range: 3.8516. Min Range: -3.8516

Max Act: 3.7153. Min Act: -0.1700

Data Index: 386946 (Open Web Text)

Max Activating Token Index: 527

Text #13

Max Range: 3.8516. Min Range: -3.8516

Max Act: 3.7169. Min Act: -0.1700

Data Index: 7406236 (Open Web Text)

Max Activating Token Index: 493

Text #14

Max Range: 3.8516. Min Range: -3.8516

Max Act: 3.7137. Min Act: -0.1700

Data Index: 2193823 (Open Web Text)

Max Activating Token Index: 342

Text #15

Max Range: 3.8516. Min Range: -3.8516

Max Act: 3.7051. Min Act: -0.1700

Data Index: 8598677 (Open Web Text)

Max Activating Token Index: 281

Text #16

Max Range: 3.8516. Min Range: -3.8516

Max Act: 3.7250. Min Act: -0.1700

Data Index: 8729860 (Open Web Text)

Max Activating Token Index: 422

Text #17

Max Range: 3.8516. Min Range: -3.8516

Max Act: 3.7355. Min Act: -0.1700

Data Index: 6062130 (Open Web Text)

Max Activating Token Index: 607

Text #18

Max Range: 3.8516. Min Range: -3.8516

Max Act: 3.7448. Min Act: -0.1700

Data Index: 3628672 (Open Web Text)

Max Activating Token Index: 576

Text #19

Max Range: 3.8516. Min Range: -3.8516

Max Act: 3.7418. Min Act: -0.1700

Data Index: 2052587 (Open Web Text)

Max Activating Token Index: 337