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

Dataset: Open Web Text

Neuron 1460 in Layer 1

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: 1.5353. Min Range: -1.5353

Max Act: 1.5353. Min Act: -0.1700

Data Index: 608627 (Open Web Text)

Max Activating Token Index: 493

Text #1

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.5154. Min Act: -0.1700

Data Index: 4238472 (Open Web Text)

Max Activating Token Index: 50

Text #2

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.4827. Min Act: -0.1694

Data Index: 8503589 (Open Web Text)

Max Activating Token Index: 437

Text #3

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.4882. Min Act: -0.1700

Data Index: 5098153 (Open Web Text)

Max Activating Token Index: 439

Text #4

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.4858. Min Act: -0.1700

Data Index: 5620346 (Open Web Text)

Max Activating Token Index: 490

Text #5

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.4729. Min Act: -0.1700

Data Index: 7482156 (Open Web Text)

Max Activating Token Index: 337

Text #6

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.4713. Min Act: -0.1682

Data Index: 1414905 (Open Web Text)

Max Activating Token Index: 413

Text #7

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.4548. Min Act: -0.1700

Data Index: 2767134 (Open Web Text)

Max Activating Token Index: 340

Text #8

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.4628. Min Act: -0.1700

Data Index: 1721016 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.4593. Min Act: -0.1696

Data Index: 2771327 (Open Web Text)

Max Activating Token Index: 503

Text #10

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.4531. Min Act: -0.1700

Data Index: 7403011 (Open Web Text)

Max Activating Token Index: 231

Text #11

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.4573. Min Act: -0.1699

Data Index: 6945861 (Open Web Text)

Max Activating Token Index: 953

Text #12

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.4459. Min Act: -0.1693

Data Index: 2891647 (Open Web Text)

Max Activating Token Index: 152

Text #13

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.4505. Min Act: -0.1700

Data Index: 8712525 (Open Web Text)

Max Activating Token Index: 544

Text #14

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.4390. Min Act: -0.1699

Data Index: 344394 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.4418. Min Act: -0.1700

Data Index: 6000958 (Open Web Text)

Max Activating Token Index: 120

Text #16

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.4428. Min Act: -0.1700

Data Index: 6855085 (Open Web Text)

Max Activating Token Index: 21

Text #17

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.4303. Min Act: -0.1700

Data Index: 4165115 (Open Web Text)

Max Activating Token Index: 757

Text #18

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.4322. Min Act: -0.1700

Data Index: 3977914 (Open Web Text)

Max Activating Token Index: 961

Text #19

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.4347. Min Act: -0.1699

Data Index: 1039592 (Open Web Text)

Max Activating Token Index: 593