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

Dataset: Open Web Text

Neuron 1460 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: 1.4390. Min Range: -1.4390

Max Act: 1.4390. Min Act: -0.1145

Data Index: 7624455 (Open Web Text)

Max Activating Token Index: 561

Text #1

Max Range: 1.4390. Min Range: -1.4390

Max Act: 1.4389. Min Act: -0.1270

Data Index: 8255001 (Open Web Text)

Max Activating Token Index: 459

Text #2

Max Range: 1.4390. Min Range: -1.4390

Max Act: 1.4296. Min Act: -0.0743

Data Index: 1729911 (Open Web Text)

Max Activating Token Index: 518

Text #3

Max Range: 1.4390. Min Range: -1.4390

Max Act: 1.4195. Min Act: -0.1316

Data Index: 6387675 (Open Web Text)

Max Activating Token Index: 541

Text #4

Max Range: 1.4390. Min Range: -1.4390

Max Act: 1.4161. Min Act: -0.1159

Data Index: 1198774 (Open Web Text)

Max Activating Token Index: 577

Text #5

Max Range: 1.4390. Min Range: -1.4390

Max Act: 1.4100. Min Act: -0.1458

Data Index: 6055394 (Open Web Text)

Max Activating Token Index: 620

Text #6

Max Range: 1.4390. Min Range: -1.4390

Max Act: 1.4109. Min Act: -0.1318

Data Index: 1227113 (Open Web Text)

Max Activating Token Index: 656

Text #7

Max Range: 1.4390. Min Range: -1.4390

Max Act: 1.3984. Min Act: -0.1528

Data Index: 5247058 (Open Web Text)

Max Activating Token Index: 523

Text #8

Max Range: 1.4390. Min Range: -1.4390

Max Act: 1.4048. Min Act: -0.1684

Data Index: 3904215 (Open Web Text)

Max Activating Token Index: 509

Text #9

Max Range: 1.4390. Min Range: -1.4390

Max Act: 1.3933. Min Act: -0.1423

Data Index: 6752617 (Open Web Text)

Max Activating Token Index: 502

Text #10

Max Range: 1.4390. Min Range: -1.4390

Max Act: 1.3946. Min Act: -0.1068

Data Index: 2998382 (Open Web Text)

Max Activating Token Index: 499

Text #11

Max Range: 1.4390. Min Range: -1.4390

Max Act: 1.3920. Min Act: -0.1198

Data Index: 686783 (Open Web Text)

Max Activating Token Index: 487

Text #12

Max Range: 1.4390. Min Range: -1.4390

Max Act: 1.3943. Min Act: -0.1430

Data Index: 2517581 (Open Web Text)

Max Activating Token Index: 514

Text #13

Max Range: 1.4390. Min Range: -1.4390

Max Act: 1.3906. Min Act: -0.1666

Data Index: 7078345 (Open Web Text)

Max Activating Token Index: 519

Text #14

Max Range: 1.4390. Min Range: -1.4390

Max Act: 1.3861. Min Act: -0.1571

Data Index: 5564435 (Open Web Text)

Max Activating Token Index: 527

Text #15

Max Range: 1.4390. Min Range: -1.4390

Max Act: 1.3795. Min Act: -0.1579

Data Index: 3877917 (Open Web Text)

Max Activating Token Index: 588

Text #16

Max Range: 1.4390. Min Range: -1.4390

Max Act: 1.3931. Min Act: -0.0983

Data Index: 2305908 (Open Web Text)

Max Activating Token Index: 508

Text #17

Max Range: 1.4390. Min Range: -1.4390

Max Act: 1.3893. Min Act: -0.0224

Data Index: 3812227 (Open Web Text)

Max Activating Token Index: 556

Text #18

Max Range: 1.4390. Min Range: -1.4390

Max Act: 1.3791. Min Act: -0.1549

Data Index: 3516518 (Open Web Text)

Max Activating Token Index: 507

Text #19

Max Range: 1.4390. Min Range: -1.4390

Max Act: 1.3797. Min Act: -0.1545

Data Index: 3407376 (Open Web Text)

Max Activating Token Index: 522