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

Dataset: Open Web Text

Neuron 556 in Layer 3

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: 2.3041. Min Range: -2.3041

Max Act: 2.3041. Min Act: -0.1700

Data Index: 931028 (Open Web Text)

Max Activating Token Index: 361

Text #1

Max Range: 2.3041. Min Range: -2.3041

Max Act: 2.2793. Min Act: -0.1700

Data Index: 4646485 (Open Web Text)

Max Activating Token Index: 157

Text #2

Max Range: 2.3041. Min Range: -2.3041

Max Act: 2.2555. Min Act: -0.1700

Data Index: 2811445 (Open Web Text)

Max Activating Token Index: 675

Text #3

Max Range: 2.3041. Min Range: -2.3041

Max Act: 2.2364. Min Act: -0.1699

Data Index: 4669460 (Open Web Text)

Max Activating Token Index: 308

Text #4

Max Range: 2.3041. Min Range: -2.3041

Max Act: 2.1998. Min Act: -0.1700

Data Index: 2363889 (Open Web Text)

Max Activating Token Index: 406

Text #5

Max Range: 2.3041. Min Range: -2.3041

Max Act: 2.1925. Min Act: -0.1700

Data Index: 7312245 (Open Web Text)

Max Activating Token Index: 634

Text #6

Max Range: 2.3041. Min Range: -2.3041

Max Act: 2.1928. Min Act: -0.1700

Data Index: 1881892 (Open Web Text)

Max Activating Token Index: 673

Text #7

Max Range: 2.3041. Min Range: -2.3041

Max Act: 2.1950. Min Act: -0.1700

Data Index: 977005 (Open Web Text)

Max Activating Token Index: 910

Text #8

Max Range: 2.3041. Min Range: -2.3041

Max Act: 2.2013. Min Act: -0.1700

Data Index: 4663664 (Open Web Text)

Max Activating Token Index: 574

Text #9

Max Range: 2.3041. Min Range: -2.3041

Max Act: 2.1694. Min Act: -0.1700

Data Index: 4433131 (Open Web Text)

Max Activating Token Index: 537

Text #10

Max Range: 2.3041. Min Range: -2.3041

Max Act: 2.1629. Min Act: -0.1700

Data Index: 6888136 (Open Web Text)

Max Activating Token Index: 526

Text #11

Max Range: 2.3041. Min Range: -2.3041

Max Act: 2.1466. Min Act: -0.1700

Data Index: 2408731 (Open Web Text)

Max Activating Token Index: 612

Text #12

Max Range: 2.3041. Min Range: -2.3041

Max Act: 2.1532. Min Act: -0.1700

Data Index: 8252366 (Open Web Text)

Max Activating Token Index: 519

Text #13

Max Range: 2.3041. Min Range: -2.3041

Max Act: 2.1446. Min Act: -0.1700

Data Index: 4817111 (Open Web Text)

Max Activating Token Index: 406

Text #14

Max Range: 2.3041. Min Range: -2.3041

Max Act: 2.1574. Min Act: -0.1700

Data Index: 7393489 (Open Web Text)

Max Activating Token Index: 385

Text #15

Max Range: 2.3041. Min Range: -2.3041

Max Act: 2.1414. Min Act: -0.1700

Data Index: 5926051 (Open Web Text)

Max Activating Token Index: 229

Text #16

Max Range: 2.3041. Min Range: -2.3041

Max Act: 2.1445. Min Act: -0.1700

Data Index: 5473773 (Open Web Text)

Max Activating Token Index: 201

Text #17

Max Range: 2.3041. Min Range: -2.3041

Max Act: 2.1457. Min Act: -0.1700

Data Index: 3036731 (Open Web Text)

Max Activating Token Index: 204

Text #18

Max Range: 2.3041. Min Range: -2.3041

Max Act: 2.1262. Min Act: -0.1700

Data Index: 7226388 (Open Web Text)

Max Activating Token Index: 480

Text #19

Max Range: 2.3041. Min Range: -2.3041

Max Act: 2.1377. Min Act: -0.1696

Data Index: 1882927 (Open Web Text)

Max Activating Token Index: 369