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

Dataset: Open Web Text

Neuron 1361 in Layer 0

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: 1.9552. Min Range: -1.9552

Max Act: 1.9552. Min Act: -0.0781

Data Index: 8305850 (Open Web Text)

Max Activating Token Index: 480

Text #1

Max Range: 1.9552. Min Range: -1.9552

Max Act: 1.7186. Min Act: -0.0157

Data Index: 5477444 (Open Web Text)

Max Activating Token Index: 952

Text #2

Max Range: 1.9552. Min Range: -1.9552

Max Act: 1.7020. Min Act: -0.1397

Data Index: 2949616 (Open Web Text)

Max Activating Token Index: 928

Text #3

Max Range: 1.9552. Min Range: -1.9552

Max Act: 1.7108. Min Act: -0.0972

Data Index: 5878213 (Open Web Text)

Max Activating Token Index: 517

Text #4

Max Range: 1.9552. Min Range: -1.9552

Max Act: 1.7081. Min Act: -0.1340

Data Index: 2861973 (Open Web Text)

Max Activating Token Index: 473

Text #5

Max Range: 1.9552. Min Range: -1.9552

Max Act: 1.7027. Min Act: -0.0395

Data Index: 6779933 (Open Web Text)

Max Activating Token Index: 463

Text #6

Max Range: 1.9552. Min Range: -1.9552

Max Act: 1.6938. Min Act: -0.0721

Data Index: 6785526 (Open Web Text)

Max Activating Token Index: 574

Text #7

Max Range: 1.9552. Min Range: -1.9552

Max Act: 1.6805. Min Act: 0.0222

Data Index: 3617746 (Open Web Text)

Max Activating Token Index: 643

Text #8

Max Range: 1.9552. Min Range: -1.9552

Max Act: 1.6793. Min Act: -0.0167

Data Index: 4938692 (Open Web Text)

Max Activating Token Index: 543

Text #9

Max Range: 1.9552. Min Range: -1.9552

Max Act: 1.6769. Min Act: -0.1669

Data Index: 4938689 (Open Web Text)

Max Activating Token Index: 618

Text #10

Max Range: 1.9552. Min Range: -1.9552

Max Act: 1.6685. Min Act: 0.0182

Data Index: 4460253 (Open Web Text)

Max Activating Token Index: 950

Text #11

Max Range: 1.9552. Min Range: -1.9552

Max Act: 1.6626. Min Act: 0.0043

Data Index: 1134224 (Open Web Text)

Max Activating Token Index: 985

Text #12

Max Range: 1.9552. Min Range: -1.9552

Max Act: 1.6615. Min Act: -0.0064

Data Index: 4938697 (Open Web Text)

Max Activating Token Index: 849

Text #13

Max Range: 1.9552. Min Range: -1.9552

Max Act: 1.6749. Min Act: -0.0750

Data Index: 6591157 (Open Web Text)

Max Activating Token Index: 450

Text #14

Max Range: 1.9552. Min Range: -1.9552

Max Act: 1.6682. Min Act: -0.1682

Data Index: 4091311 (Open Web Text)

Max Activating Token Index: 808

Text #15

Max Range: 1.9552. Min Range: -1.9552

Max Act: 1.6642. Min Act: -0.0464

Data Index: 249274 (Open Web Text)

Max Activating Token Index: 633

Text #16

Max Range: 1.9552. Min Range: -1.9552

Max Act: 1.6632. Min Act: -0.0706

Data Index: 4663466 (Open Web Text)

Max Activating Token Index: 595

Text #17

Max Range: 1.9552. Min Range: -1.9552

Max Act: 1.6682. Min Act: -0.0168

Data Index: 4938704 (Open Web Text)

Max Activating Token Index: 749

Text #18

Max Range: 1.9552. Min Range: -1.9552

Max Act: 1.6661. Min Act: -0.0781

Data Index: 4737510 (Open Web Text)

Max Activating Token Index: 604

Text #19

Max Range: 1.9552. Min Range: -1.9552

Max Act: 1.6652. Min Act: -0.1538

Data Index: 2460510 (Open Web Text)

Max Activating Token Index: 264