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

Dataset: Open Web Text

Neuron 427 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: 1.5623. Min Range: -1.5623

Max Act: 1.5623. Min Act: -0.1700

Data Index: 5057503 (Open Web Text)

Max Activating Token Index: 678

Text #1

Max Range: 1.5623. Min Range: -1.5623

Max Act: 1.5389. Min Act: -0.1700

Data Index: 1746217 (Open Web Text)

Max Activating Token Index: 428

Text #2

Max Range: 1.5623. Min Range: -1.5623

Max Act: 1.5389. Min Act: -0.1698

Data Index: 5357985 (Open Web Text)

Max Activating Token Index: 776

Text #3

Max Range: 1.5623. Min Range: -1.5623

Max Act: 1.5021. Min Act: -0.1699

Data Index: 5335016 (Open Web Text)

Max Activating Token Index: 450

Text #4

Max Range: 1.5623. Min Range: -1.5623

Max Act: 1.5041. Min Act: -0.1700

Data Index: 7230244 (Open Web Text)

Max Activating Token Index: 288

Text #5

Max Range: 1.5623. Min Range: -1.5623

Max Act: 1.4892. Min Act: -0.1700

Data Index: 2275994 (Open Web Text)

Max Activating Token Index: 195

Text #6

Max Range: 1.5623. Min Range: -1.5623

Max Act: 1.4956. Min Act: -0.1698

Data Index: 6826545 (Open Web Text)

Max Activating Token Index: 757

Text #7

Max Range: 1.5623. Min Range: -1.5623

Max Act: 1.4820. Min Act: -0.1700

Data Index: 2431750 (Open Web Text)

Max Activating Token Index: 200

Text #8

Max Range: 1.5623. Min Range: -1.5623

Max Act: 1.4877. Min Act: -0.1700

Data Index: 6673116 (Open Web Text)

Max Activating Token Index: 711

Text #9

Max Range: 1.5623. Min Range: -1.5623

Max Act: 1.4904. Min Act: -0.1700

Data Index: 1528671 (Open Web Text)

Max Activating Token Index: 610

Text #10

Max Range: 1.5623. Min Range: -1.5623

Max Act: 1.4749. Min Act: -0.1700

Data Index: 2058316 (Open Web Text)

Max Activating Token Index: 179

Text #11

Max Range: 1.5623. Min Range: -1.5623

Max Act: 1.4596. Min Act: -0.1700

Data Index: 2436762 (Open Web Text)

Max Activating Token Index: 740

Text #12

Max Range: 1.5623. Min Range: -1.5623

Max Act: 1.4680. Min Act: -0.1700

Data Index: 6730271 (Open Web Text)

Max Activating Token Index: 731

Text #13

Max Range: 1.5623. Min Range: -1.5623

Max Act: 1.4688. Min Act: -0.1700

Data Index: 6862546 (Open Web Text)

Max Activating Token Index: 708

Text #14

Max Range: 1.5623. Min Range: -1.5623

Max Act: 1.4528. Min Act: -0.1700

Data Index: 4555330 (Open Web Text)

Max Activating Token Index: 326

Text #15

Max Range: 1.5623. Min Range: -1.5623

Max Act: 1.4591. Min Act: -0.1700

Data Index: 8755590 (Open Web Text)

Max Activating Token Index: 622

Text #16

Max Range: 1.5623. Min Range: -1.5623

Max Act: 1.4556. Min Act: -0.1700

Data Index: 2461058 (Open Web Text)

Max Activating Token Index: 416

Text #17

Max Range: 1.5623. Min Range: -1.5623

Max Act: 1.4491. Min Act: -0.1700

Data Index: 1948728 (Open Web Text)

Max Activating Token Index: 605

Text #18

Max Range: 1.5623. Min Range: -1.5623

Max Act: 1.4392. Min Act: -0.1700

Data Index: 1672957 (Open Web Text)

Max Activating Token Index: 346

Text #19

Max Range: 1.5623. Min Range: -1.5623

Max Act: 1.4456. Min Act: -0.1700

Data Index: 7585527 (Open Web Text)

Max Activating Token Index: 447