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

Dataset: Open Web Text

Neuron 2792 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: 3.1163. Min Range: -3.1163

Max Act: 3.1163. Min Act: -0.1699

Data Index: 6523443 (Open Web Text)

Max Activating Token Index: 548

Text #1

Max Range: 3.1163. Min Range: -3.1163

Max Act: 2.8866. Min Act: 0.0868

Data Index: 4624784 (Open Web Text)

Max Activating Token Index: 507

Text #2

Max Range: 3.1163. Min Range: -3.1163

Max Act: 2.8563. Min Act: -0.1700

Data Index: 1845864 (Open Web Text)

Max Activating Token Index: 175

Text #3

Max Range: 3.1163. Min Range: -3.1163

Max Act: 2.8334. Min Act: 0.0868

Data Index: 4624782 (Open Web Text)

Max Activating Token Index: 486

Text #4

Max Range: 3.1163. Min Range: -3.1163

Max Act: 2.8420. Min Act: -0.1700

Data Index: 4624786 (Open Web Text)

Max Activating Token Index: 563

Text #5

Max Range: 3.1163. Min Range: -3.1163

Max Act: 2.8168. Min Act: 0.0868

Data Index: 4624785 (Open Web Text)

Max Activating Token Index: 508

Text #6

Max Range: 3.1163. Min Range: -3.1163

Max Act: 2.8014. Min Act: -0.1448

Data Index: 2249770 (Open Web Text)

Max Activating Token Index: 783

Text #7

Max Range: 3.1163. Min Range: -3.1163

Max Act: 2.8076. Min Act: 0.0868

Data Index: 4624783 (Open Web Text)

Max Activating Token Index: 540

Text #8

Max Range: 3.1163. Min Range: -3.1163

Max Act: 2.8072. Min Act: 0.0868

Data Index: 4624776 (Open Web Text)

Max Activating Token Index: 403

Text #9

Max Range: 3.1163. Min Range: -3.1163

Max Act: 2.7844. Min Act: -0.1700

Data Index: 7820565 (Open Web Text)

Max Activating Token Index: 273

Text #10

Max Range: 3.1163. Min Range: -3.1163

Max Act: 2.7346. Min Act: -0.1633

Data Index: 1383010 (Open Web Text)

Max Activating Token Index: 703

Text #11

Max Range: 3.1163. Min Range: -3.1163

Max Act: 2.7522. Min Act: 0.0868

Data Index: 4624774 (Open Web Text)

Max Activating Token Index: 552

Text #12

Max Range: 3.1163. Min Range: -3.1163

Max Act: 2.7512. Min Act: 0.0868

Data Index: 4624781 (Open Web Text)

Max Activating Token Index: 478

Text #13

Max Range: 3.1163. Min Range: -3.1163

Max Act: 2.7364. Min Act: -0.1700

Data Index: 2478168 (Open Web Text)

Max Activating Token Index: 784

Text #14

Max Range: 3.1163. Min Range: -3.1163

Max Act: 2.7355. Min Act: 0.0868

Data Index: 4624777 (Open Web Text)

Max Activating Token Index: 508

Text #15

Max Range: 3.1163. Min Range: -3.1163

Max Act: 2.7218. Min Act: 0.0868

Data Index: 4624775 (Open Web Text)

Max Activating Token Index: 505

Text #16

Max Range: 3.1163. Min Range: -3.1163

Max Act: 2.7043. Min Act: -0.1700

Data Index: 830030 (Open Web Text)

Max Activating Token Index: 106

Text #17

Max Range: 3.1163. Min Range: -3.1163

Max Act: 2.6982. Min Act: -0.1667

Data Index: 4428509 (Open Web Text)

Max Activating Token Index: 588

Text #18

Max Range: 3.1163. Min Range: -3.1163

Max Act: 2.7087. Min Act: -0.1412

Data Index: 7135428 (Open Web Text)

Max Activating Token Index: 1022

Text #19

Max Range: 3.1163. Min Range: -3.1163

Max Act: 2.6845. Min Act: -0.1672

Data Index: 3333499 (Open Web Text)

Max Activating Token Index: 528