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

Dataset: Open Web Text

Neuron 2438 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: 3.3208. Min Range: -3.3208

Max Act: 3.3208. Min Act: -0.1700

Data Index: 5704833 (Open Web Text)

Max Activating Token Index: 756

Text #1

Max Range: 3.3208. Min Range: -3.3208

Max Act: 3.2929. Min Act: -0.1700

Data Index: 3260340 (Open Web Text)

Max Activating Token Index: 443

Text #2

Max Range: 3.3208. Min Range: -3.3208

Max Act: 3.2904. Min Act: -0.1700

Data Index: 3279392 (Open Web Text)

Max Activating Token Index: 577

Text #3

Max Range: 3.3208. Min Range: -3.3208

Max Act: 3.2542. Min Act: -0.1700

Data Index: 4017558 (Open Web Text)

Max Activating Token Index: 541

Text #4

Max Range: 3.3208. Min Range: -3.3208

Max Act: 3.2570. Min Act: -0.1700

Data Index: 7135558 (Open Web Text)

Max Activating Token Index: 662

Text #5

Max Range: 3.3208. Min Range: -3.3208

Max Act: 3.2289. Min Act: -0.1700

Data Index: 4958469 (Open Web Text)

Max Activating Token Index: 601

Text #6

Max Range: 3.3208. Min Range: -3.3208

Max Act: 3.2555. Min Act: -0.1700

Data Index: 1488760 (Open Web Text)

Max Activating Token Index: 374

Text #7

Max Range: 3.3208. Min Range: -3.3208

Max Act: 3.2632. Min Act: -0.1700

Data Index: 5351142 (Open Web Text)

Max Activating Token Index: 531

Text #8

Max Range: 3.3208. Min Range: -3.3208

Max Act: 3.2619. Min Act: -0.1700

Data Index: 5704834 (Open Web Text)

Max Activating Token Index: 455

Text #9

Max Range: 3.3208. Min Range: -3.3208

Max Act: 3.2867. Min Act: -0.1700

Data Index: 3565748 (Open Web Text)

Max Activating Token Index: 805

Text #10

Max Range: 3.3208. Min Range: -3.3208

Max Act: 3.2670. Min Act: -0.1700

Data Index: 7265928 (Open Web Text)

Max Activating Token Index: 403

Text #11

Max Range: 3.3208. Min Range: -3.3208

Max Act: 3.2362. Min Act: -0.1700

Data Index: 6795579 (Open Web Text)

Max Activating Token Index: 577

Text #12

Max Range: 3.3208. Min Range: -3.3208

Max Act: 3.2089. Min Act: -0.1700

Data Index: 8581977 (Open Web Text)

Max Activating Token Index: 354

Text #13

Max Range: 3.3208. Min Range: -3.3208

Max Act: 3.2164. Min Act: -0.1700

Data Index: 5441535 (Open Web Text)

Max Activating Token Index: 926

Text #14

Max Range: 3.3208. Min Range: -3.3208

Max Act: 3.2230. Min Act: -0.1700

Data Index: 4428059 (Open Web Text)

Max Activating Token Index: 371

Text #15

Max Range: 3.3208. Min Range: -3.3208

Max Act: 3.2211. Min Act: -0.1700

Data Index: 5437363 (Open Web Text)

Max Activating Token Index: 379

Text #16

Max Range: 3.3208. Min Range: -3.3208

Max Act: 3.2310. Min Act: -0.1700

Data Index: 7193046 (Open Web Text)

Max Activating Token Index: 495

Text #17

Max Range: 3.3208. Min Range: -3.3208

Max Act: 3.2163. Min Act: -0.1700

Data Index: 4140954 (Open Web Text)

Max Activating Token Index: 808

Text #18

Max Range: 3.3208. Min Range: -3.3208

Max Act: 3.2161. Min Act: -0.1700

Data Index: 4652547 (Open Web Text)

Max Activating Token Index: 252

Text #19

Max Range: 3.3208. Min Range: -3.3208

Max Act: 3.2128. Min Act: -0.1700

Data Index: 4712253 (Open Web Text)

Max Activating Token Index: 334