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

Dataset: Open Web Text

Neuron 2419 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: 3.6398. Min Range: -3.6398

Max Act: 3.6287. Min Act: -0.1700

Data Index: 7153707 (Open Web Text)

Max Activating Token Index: 19

Text #1

Max Range: 3.6398. Min Range: -3.6398

Max Act: 3.6398. Min Act: -0.1700

Data Index: 3717702 (Open Web Text)

Max Activating Token Index: 699

Text #2

Max Range: 3.6398. Min Range: -3.6398

Max Act: 3.5787. Min Act: -0.1700

Data Index: 2869883 (Open Web Text)

Max Activating Token Index: 962

Text #3

Max Range: 3.6398. Min Range: -3.6398

Max Act: 3.5312. Min Act: -0.1700

Data Index: 6761201 (Open Web Text)

Max Activating Token Index: 751

Text #4

Max Range: 3.6398. Min Range: -3.6398

Max Act: 3.5493. Min Act: -0.1700

Data Index: 363832 (Open Web Text)

Max Activating Token Index: 257

Text #5

Max Range: 3.6398. Min Range: -3.6398

Max Act: 3.5317. Min Act: -0.1700

Data Index: 4580076 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 3.6398. Min Range: -3.6398

Max Act: 3.5442. Min Act: -0.1700

Data Index: 4517284 (Open Web Text)

Max Activating Token Index: 39

Text #7

Max Range: 3.6398. Min Range: -3.6398

Max Act: 3.5461. Min Act: -0.1700

Data Index: 7777062 (Open Web Text)

Max Activating Token Index: 327

Text #8

Max Range: 3.6398. Min Range: -3.6398

Max Act: 3.5124. Min Act: -0.1700

Data Index: 5077990 (Open Web Text)

Max Activating Token Index: 656

Text #9

Max Range: 3.6398. Min Range: -3.6398

Max Act: 3.4596. Min Act: -0.1700

Data Index: 8678358 (Open Web Text)

Max Activating Token Index: 732

Text #10

Max Range: 3.6398. Min Range: -3.6398

Max Act: 3.4557. Min Act: -0.1700

Data Index: 5087535 (Open Web Text)

Max Activating Token Index: 129

Text #11

Max Range: 3.6398. Min Range: -3.6398

Max Act: 3.4631. Min Act: -0.1700

Data Index: 8459922 (Open Web Text)

Max Activating Token Index: 646

Text #12

Max Range: 3.6398. Min Range: -3.6398

Max Act: 3.4551. Min Act: -0.1700

Data Index: 3939613 (Open Web Text)

Max Activating Token Index: 507

Text #13

Max Range: 3.6398. Min Range: -3.6398

Max Act: 3.4586. Min Act: -0.1700

Data Index: 2436704 (Open Web Text)

Max Activating Token Index: 401

Text #14

Max Range: 3.6398. Min Range: -3.6398

Max Act: 3.4459. Min Act: -0.1700

Data Index: 3351316 (Open Web Text)

Max Activating Token Index: 481

Text #15

Max Range: 3.6398. Min Range: -3.6398

Max Act: 3.4468. Min Act: -0.1700

Data Index: 3478007 (Open Web Text)

Max Activating Token Index: 782

Text #16

Max Range: 3.6398. Min Range: -3.6398

Max Act: 3.4641. Min Act: -0.1700

Data Index: 8535333 (Open Web Text)

Max Activating Token Index: 814

Text #17

Max Range: 3.6398. Min Range: -3.6398

Max Act: 3.4236. Min Act: -0.1700

Data Index: 6000928 (Open Web Text)

Max Activating Token Index: 323

Text #18

Max Range: 3.6398. Min Range: -3.6398

Max Act: 3.4268. Min Act: -0.1700

Data Index: 5150603 (Open Web Text)

Max Activating Token Index: 864

Text #19

Max Range: 3.6398. Min Range: -3.6398

Max Act: 3.4096. Min Act: -0.1700

Data Index: 4056467 (Open Web Text)

Max Activating Token Index: 625