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

Dataset: Open Web Text

Neuron 3022 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: 3.9916. Min Range: -3.9916

Max Act: 3.9916. Min Act: -0.1700

Data Index: 8344756 (Open Web Text)

Max Activating Token Index: 858

Text #1

Max Range: 3.9916. Min Range: -3.9916

Max Act: 3.9533. Min Act: -0.1700

Data Index: 298374 (Open Web Text)

Max Activating Token Index: 603

Text #2

Max Range: 3.9916. Min Range: -3.9916

Max Act: 3.9272. Min Act: -0.1700

Data Index: 2736096 (Open Web Text)

Max Activating Token Index: 174

Text #3

Max Range: 3.9916. Min Range: -3.9916

Max Act: 3.8949. Min Act: -0.1700

Data Index: 7477864 (Open Web Text)

Max Activating Token Index: 209

Text #4

Max Range: 3.9916. Min Range: -3.9916

Max Act: 3.9280. Min Act: -0.1700

Data Index: 7453560 (Open Web Text)

Max Activating Token Index: 431

Text #5

Max Range: 3.9916. Min Range: -3.9916

Max Act: 3.8923. Min Act: -0.1700

Data Index: 4737429 (Open Web Text)

Max Activating Token Index: 159

Text #6

Max Range: 3.9916. Min Range: -3.9916

Max Act: 3.8670. Min Act: -0.1700

Data Index: 4863586 (Open Web Text)

Max Activating Token Index: 508

Text #7

Max Range: 3.9916. Min Range: -3.9916

Max Act: 3.8687. Min Act: -0.1700

Data Index: 8820985 (Open Web Text)

Max Activating Token Index: 445

Text #8

Max Range: 3.9916. Min Range: -3.9916

Max Act: 3.8666. Min Act: -0.1700

Data Index: 5528402 (Open Web Text)

Max Activating Token Index: 202

Text #9

Max Range: 3.9916. Min Range: -3.9916

Max Act: 3.8794. Min Act: -0.1700

Data Index: 8648194 (Open Web Text)

Max Activating Token Index: 433

Text #10

Max Range: 3.9916. Min Range: -3.9916

Max Act: 3.8658. Min Act: -0.1700

Data Index: 3674187 (Open Web Text)

Max Activating Token Index: 320

Text #11

Max Range: 3.9916. Min Range: -3.9916

Max Act: 3.8833. Min Act: -0.1700

Data Index: 3521872 (Open Web Text)

Max Activating Token Index: 337

Text #12

Max Range: 3.9916. Min Range: -3.9916

Max Act: 3.8469. Min Act: -0.1700

Data Index: 1024564 (Open Web Text)

Max Activating Token Index: 575

Text #13

Max Range: 3.9916. Min Range: -3.9916

Max Act: 3.8477. Min Act: -0.1700

Data Index: 5711066 (Open Web Text)

Max Activating Token Index: 381

Text #14

Max Range: 3.9916. Min Range: -3.9916

Max Act: 3.8391. Min Act: -0.1700

Data Index: 5849804 (Open Web Text)

Max Activating Token Index: 408

Text #15

Max Range: 3.9916. Min Range: -3.9916

Max Act: 3.8352. Min Act: -0.1700

Data Index: 2404652 (Open Web Text)

Max Activating Token Index: 603

Text #16

Max Range: 3.9916. Min Range: -3.9916

Max Act: 3.8329. Min Act: -0.1700

Data Index: 2570458 (Open Web Text)

Max Activating Token Index: 246

Text #17

Max Range: 3.9916. Min Range: -3.9916

Max Act: 3.8318. Min Act: -0.1700

Data Index: 2651858 (Open Web Text)

Max Activating Token Index: 159

Text #18

Max Range: 3.9916. Min Range: -3.9916

Max Act: 3.8585. Min Act: -0.1700

Data Index: 6108351 (Open Web Text)

Max Activating Token Index: 110

Text #19

Max Range: 3.9916. Min Range: -3.9916

Max Act: 3.8434. Min Act: -0.1700

Data Index: 7087130 (Open Web Text)

Max Activating Token Index: 693