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

Dataset: Open Web Text

Neuron 823 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: 3.0930. Min Range: -3.0930

Max Act: 3.0930. Min Act: -0.1700

Data Index: 1829070 (Open Web Text)

Max Activating Token Index: 768

Text #1

Max Range: 3.0930. Min Range: -3.0930

Max Act: 2.9678. Min Act: -0.1700

Data Index: 2848369 (Open Web Text)

Max Activating Token Index: 44

Text #2

Max Range: 3.0930. Min Range: -3.0930

Max Act: 2.9502. Min Act: -0.1700

Data Index: 8189811 (Open Web Text)

Max Activating Token Index: 537

Text #3

Max Range: 3.0930. Min Range: -3.0930

Max Act: 2.9310. Min Act: -0.1700

Data Index: 2232586 (Open Web Text)

Max Activating Token Index: 723

Text #4

Max Range: 3.0930. Min Range: -3.0930

Max Act: 2.9403. Min Act: -0.1700

Data Index: 8645238 (Open Web Text)

Max Activating Token Index: 392

Text #5

Max Range: 3.0930. Min Range: -3.0930

Max Act: 2.9322. Min Act: -0.1700

Data Index: 7747271 (Open Web Text)

Max Activating Token Index: 716

Text #6

Max Range: 3.0930. Min Range: -3.0930

Max Act: 2.8844. Min Act: -0.1700

Data Index: 4552286 (Open Web Text)

Max Activating Token Index: 900

Text #7

Max Range: 3.0930. Min Range: -3.0930

Max Act: 2.8790. Min Act: -0.1700

Data Index: 5805190 (Open Web Text)

Max Activating Token Index: 554

Text #8

Max Range: 3.0930. Min Range: -3.0930

Max Act: 2.8659. Min Act: -0.1700

Data Index: 8523000 (Open Web Text)

Max Activating Token Index: 813

Text #9

Max Range: 3.0930. Min Range: -3.0930

Max Act: 2.8417. Min Act: -0.1700

Data Index: 2687591 (Open Web Text)

Max Activating Token Index: 534

Text #10

Max Range: 3.0930. Min Range: -3.0930

Max Act: 2.8661. Min Act: -0.1700

Data Index: 420461 (Open Web Text)

Max Activating Token Index: 873

Text #11

Max Range: 3.0930. Min Range: -3.0930

Max Act: 2.8414. Min Act: -0.1700

Data Index: 3360568 (Open Web Text)

Max Activating Token Index: 883

Text #12

Max Range: 3.0930. Min Range: -3.0930

Max Act: 2.8312. Min Act: -0.1700

Data Index: 898529 (Open Web Text)

Max Activating Token Index: 598

Text #13

Max Range: 3.0930. Min Range: -3.0930

Max Act: 2.8360. Min Act: -0.1700

Data Index: 3636366 (Open Web Text)

Max Activating Token Index: 755

Text #14

Max Range: 3.0930. Min Range: -3.0930

Max Act: 2.8333. Min Act: -0.1700

Data Index: 4728491 (Open Web Text)

Max Activating Token Index: 423

Text #15

Max Range: 3.0930. Min Range: -3.0930

Max Act: 2.8474. Min Act: -0.1700

Data Index: 6611194 (Open Web Text)

Max Activating Token Index: 444

Text #16

Max Range: 3.0930. Min Range: -3.0930

Max Act: 2.8163. Min Act: -0.1700

Data Index: 1744756 (Open Web Text)

Max Activating Token Index: 1003

Text #17

Max Range: 3.0930. Min Range: -3.0930

Max Act: 2.8199. Min Act: -0.1700

Data Index: 302335 (Open Web Text)

Max Activating Token Index: 424

Text #18

Max Range: 3.0930. Min Range: -3.0930

Max Act: 2.8284. Min Act: -0.1700

Data Index: 5128812 (Open Web Text)

Max Activating Token Index: 445

Text #19

Max Range: 3.0930. Min Range: -3.0930

Max Act: 2.8157. Min Act: -0.1700

Data Index: 7422472 (Open Web Text)

Max Activating Token Index: 392