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

Dataset: Open Web Text

Neuron 2091 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: 3.8458. Min Range: -3.8458

Max Act: 3.8458. Min Act: -0.1700

Data Index: 6431928 (Open Web Text)

Max Activating Token Index: 447

Text #1

Max Range: 3.8458. Min Range: -3.8458

Max Act: 3.8345. Min Act: -0.1700

Data Index: 7088198 (Open Web Text)

Max Activating Token Index: 848

Text #2

Max Range: 3.8458. Min Range: -3.8458

Max Act: 3.8318. Min Act: -0.1700

Data Index: 6249748 (Open Web Text)

Max Activating Token Index: 358

Text #3

Max Range: 3.8458. Min Range: -3.8458

Max Act: 3.7992. Min Act: -0.1700

Data Index: 726293 (Open Web Text)

Max Activating Token Index: 709

Text #4

Max Range: 3.8458. Min Range: -3.8458

Max Act: 3.7826. Min Act: -0.1700

Data Index: 6862796 (Open Web Text)

Max Activating Token Index: 92

Text #5

Max Range: 3.8458. Min Range: -3.8458

Max Act: 3.7844. Min Act: -0.1700

Data Index: 1321602 (Open Web Text)

Max Activating Token Index: 591

Text #6

Max Range: 3.8458. Min Range: -3.8458

Max Act: 3.7629. Min Act: -0.1700

Data Index: 1042044 (Open Web Text)

Max Activating Token Index: 337

Text #7

Max Range: 3.8458. Min Range: -3.8458

Max Act: 3.7506. Min Act: -0.1700

Data Index: 4199867 (Open Web Text)

Max Activating Token Index: 875

Text #8

Max Range: 3.8458. Min Range: -3.8458

Max Act: 3.7373. Min Act: -0.1700

Data Index: 1759703 (Open Web Text)

Max Activating Token Index: 248

Text #9

Max Range: 3.8458. Min Range: -3.8458

Max Act: 3.7350. Min Act: -0.1700

Data Index: 926360 (Open Web Text)

Max Activating Token Index: 329

Text #10

Max Range: 3.8458. Min Range: -3.8458

Max Act: 3.7275. Min Act: -0.1700

Data Index: 2618217 (Open Web Text)

Max Activating Token Index: 394

Text #11

Max Range: 3.8458. Min Range: -3.8458

Max Act: 3.7297. Min Act: -0.1700

Data Index: 3926370 (Open Web Text)

Max Activating Token Index: 457

Text #12

Max Range: 3.8458. Min Range: -3.8458

Max Act: 3.7369. Min Act: -0.1700

Data Index: 5374001 (Open Web Text)

Max Activating Token Index: 139

Text #13

Max Range: 3.8458. Min Range: -3.8458

Max Act: 3.7280. Min Act: -0.1700

Data Index: 4731499 (Open Web Text)

Max Activating Token Index: 482

Text #14

Max Range: 3.8458. Min Range: -3.8458

Max Act: 3.7258. Min Act: -0.1700

Data Index: 5039461 (Open Web Text)

Max Activating Token Index: 492

Text #15

Max Range: 3.8458. Min Range: -3.8458

Max Act: 3.7192. Min Act: -0.1700

Data Index: 1070091 (Open Web Text)

Max Activating Token Index: 332

Text #16

Max Range: 3.8458. Min Range: -3.8458

Max Act: 3.7306. Min Act: -0.1700

Data Index: 4127278 (Open Web Text)

Max Activating Token Index: 594

Text #17

Max Range: 3.8458. Min Range: -3.8458

Max Act: 3.7013. Min Act: -0.1700

Data Index: 3822712 (Open Web Text)

Max Activating Token Index: 460

Text #18

Max Range: 3.8458. Min Range: -3.8458

Max Act: 3.7004. Min Act: -0.1700

Data Index: 4958799 (Open Web Text)

Max Activating Token Index: 785

Text #19

Max Range: 3.8458. Min Range: -3.8458

Max Act: 3.7235. Min Act: -0.1700

Data Index: 1692860 (Open Web Text)

Max Activating Token Index: 651