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

Dataset: Open Web Text

Neuron 2693 in Layer 4

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: 6.1273. Min Range: -6.1273

Max Act: 6.1273. Min Act: -0.1700

Data Index: 59550 (Open Web Text)

Max Activating Token Index: 466

Text #1

Max Range: 6.1273. Min Range: -6.1273

Max Act: 6.0073. Min Act: -0.1700

Data Index: 7310255 (Open Web Text)

Max Activating Token Index: 993

Text #2

Max Range: 6.1273. Min Range: -6.1273

Max Act: 6.0809. Min Act: -0.1700

Data Index: 8416654 (Open Web Text)

Max Activating Token Index: 697

Text #3

Max Range: 6.1273. Min Range: -6.1273

Max Act: 6.1005. Min Act: -0.1700

Data Index: 5021801 (Open Web Text)

Max Activating Token Index: 429

Text #4

Max Range: 6.1273. Min Range: -6.1273

Max Act: 5.9645. Min Act: -0.1700

Data Index: 2883575 (Open Web Text)

Max Activating Token Index: 226

Text #5

Max Range: 6.1273. Min Range: -6.1273

Max Act: 5.9797. Min Act: -0.1700

Data Index: 7176927 (Open Web Text)

Max Activating Token Index: 414

Text #6

Max Range: 6.1273. Min Range: -6.1273

Max Act: 5.9026. Min Act: -0.1700

Data Index: 3078157 (Open Web Text)

Max Activating Token Index: 522

Text #7

Max Range: 6.1273. Min Range: -6.1273

Max Act: 5.9444. Min Act: -0.1700

Data Index: 7228068 (Open Web Text)

Max Activating Token Index: 565

Text #8

Max Range: 6.1273. Min Range: -6.1273

Max Act: 5.8773. Min Act: -0.1700

Data Index: 5149398 (Open Web Text)

Max Activating Token Index: 490

Text #9

Max Range: 6.1273. Min Range: -6.1273

Max Act: 5.9754. Min Act: -0.1700

Data Index: 2346163 (Open Web Text)

Max Activating Token Index: 587

Text #10

Max Range: 6.1273. Min Range: -6.1273

Max Act: 5.8583. Min Act: -0.1700

Data Index: 634113 (Open Web Text)

Max Activating Token Index: 48

Text #11

Max Range: 6.1273. Min Range: -6.1273

Max Act: 5.9055. Min Act: -0.1700

Data Index: 2159610 (Open Web Text)

Max Activating Token Index: 951

Text #12

Max Range: 6.1273. Min Range: -6.1273

Max Act: 5.8095. Min Act: -0.1700

Data Index: 5096874 (Open Web Text)

Max Activating Token Index: 22

Text #13

Max Range: 6.1273. Min Range: -6.1273

Max Act: 5.8783. Min Act: -0.1700

Data Index: 718296 (Open Web Text)

Max Activating Token Index: 247

Text #14

Max Range: 6.1273. Min Range: -6.1273

Max Act: 5.8293. Min Act: -0.1700

Data Index: 5191341 (Open Web Text)

Max Activating Token Index: 565

Text #15

Max Range: 6.1273. Min Range: -6.1273

Max Act: 5.7968. Min Act: -0.1700

Data Index: 8801726 (Open Web Text)

Max Activating Token Index: 687

Text #16

Max Range: 6.1273. Min Range: -6.1273

Max Act: 5.7189. Min Act: -0.1700

Data Index: 6595830 (Open Web Text)

Max Activating Token Index: 788

Text #17

Max Range: 6.1273. Min Range: -6.1273

Max Act: 5.7953. Min Act: -0.1700

Data Index: 1113481 (Open Web Text)

Max Activating Token Index: 194

Text #18

Max Range: 6.1273. Min Range: -6.1273

Max Act: 5.8550. Min Act: -0.1700

Data Index: 6138068 (Open Web Text)

Max Activating Token Index: 572

Text #19

Max Range: 6.1273. Min Range: -6.1273

Max Act: 5.7510. Min Act: -0.1700

Data Index: 8458023 (Open Web Text)

Max Activating Token Index: 212