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

Dataset: Open Web Text

Neuron 1685 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: 3.8631. Min Range: -3.8631

Max Act: 3.8631. Min Act: -0.1700

Data Index: 2853997 (Open Web Text)

Max Activating Token Index: 663

Text #1

Max Range: 3.8631. Min Range: -3.8631

Max Act: 3.8542. Min Act: -0.1700

Data Index: 8824995 (Open Web Text)

Max Activating Token Index: 242

Text #2

Max Range: 3.8631. Min Range: -3.8631

Max Act: 3.7606. Min Act: -0.1700

Data Index: 7840001 (Open Web Text)

Max Activating Token Index: 375

Text #3

Max Range: 3.8631. Min Range: -3.8631

Max Act: 3.7478. Min Act: -0.1700

Data Index: 2681358 (Open Web Text)

Max Activating Token Index: 204

Text #4

Max Range: 3.8631. Min Range: -3.8631

Max Act: 3.7400. Min Act: -0.1700

Data Index: 4560030 (Open Web Text)

Max Activating Token Index: 210

Text #5

Max Range: 3.8631. Min Range: -3.8631

Max Act: 3.7163. Min Act: -0.1700

Data Index: 7919303 (Open Web Text)

Max Activating Token Index: 801

Text #6

Max Range: 3.8631. Min Range: -3.8631

Max Act: 3.7146. Min Act: -0.1700

Data Index: 835826 (Open Web Text)

Max Activating Token Index: 192

Text #7

Max Range: 3.8631. Min Range: -3.8631

Max Act: 3.7020. Min Act: -0.1700

Data Index: 5807402 (Open Web Text)

Max Activating Token Index: 724

Text #8

Max Range: 3.8631. Min Range: -3.8631

Max Act: 3.6887. Min Act: -0.1700

Data Index: 6334464 (Open Web Text)

Max Activating Token Index: 289

Text #9

Max Range: 3.8631. Min Range: -3.8631

Max Act: 3.6486. Min Act: -0.1700

Data Index: 562527 (Open Web Text)

Max Activating Token Index: 871

Text #10

Max Range: 3.8631. Min Range: -3.8631

Max Act: 3.6671. Min Act: -0.1700

Data Index: 1540893 (Open Web Text)

Max Activating Token Index: 209

Text #11

Max Range: 3.8631. Min Range: -3.8631

Max Act: 3.6617. Min Act: -0.1700

Data Index: 5712990 (Open Web Text)

Max Activating Token Index: 288

Text #12

Max Range: 3.8631. Min Range: -3.8631

Max Act: 3.6529. Min Act: -0.1700

Data Index: 4520607 (Open Web Text)

Max Activating Token Index: 246

Text #13

Max Range: 3.8631. Min Range: -3.8631

Max Act: 3.6658. Min Act: -0.1700

Data Index: 6639812 (Open Web Text)

Max Activating Token Index: 590

Text #14

Max Range: 3.8631. Min Range: -3.8631

Max Act: 3.6446. Min Act: -0.1700

Data Index: 2486253 (Open Web Text)

Max Activating Token Index: 240

Text #15

Max Range: 3.8631. Min Range: -3.8631

Max Act: 3.6489. Min Act: -0.1700

Data Index: 5702825 (Open Web Text)

Max Activating Token Index: 712

Text #16

Max Range: 3.8631. Min Range: -3.8631

Max Act: 3.6521. Min Act: -0.1700

Data Index: 2853619 (Open Web Text)

Max Activating Token Index: 579

Text #17

Max Range: 3.8631. Min Range: -3.8631

Max Act: 3.6135. Min Act: -0.1700

Data Index: 600818 (Open Web Text)

Max Activating Token Index: 109

Text #18

Max Range: 3.8631. Min Range: -3.8631

Max Act: 3.6218. Min Act: -0.1700

Data Index: 7199163 (Open Web Text)

Max Activating Token Index: 593

Text #19

Max Range: 3.8631. Min Range: -3.8631

Max Act: 3.6320. Min Act: -0.1700

Data Index: 8750375 (Open Web Text)

Max Activating Token Index: 609