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

Dataset: Open Web Text

Neuron 169 in Layer 2

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: 3.8759. Min Range: -3.8759

Max Act: 3.8759. Min Act: -0.1700

Data Index: 1472375 (Open Web Text)

Max Activating Token Index: 625

Text #1

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.8479. Min Act: -0.1700

Data Index: 570964 (Open Web Text)

Max Activating Token Index: 115

Text #2

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.8416. Min Act: -0.1700

Data Index: 4626569 (Open Web Text)

Max Activating Token Index: 806

Text #3

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.7953. Min Act: -0.1700

Data Index: 6677781 (Open Web Text)

Max Activating Token Index: 982

Text #4

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.8307. Min Act: -0.1700

Data Index: 6589116 (Open Web Text)

Max Activating Token Index: 215

Text #5

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.8514. Min Act: -0.1700

Data Index: 1245596 (Open Web Text)

Max Activating Token Index: 320

Text #6

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.7740. Min Act: -0.1700

Data Index: 4907058 (Open Web Text)

Max Activating Token Index: 455

Text #7

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.8068. Min Act: -0.1700

Data Index: 3875124 (Open Web Text)

Max Activating Token Index: 782

Text #8

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.8113. Min Act: -0.1700

Data Index: 6541476 (Open Web Text)

Max Activating Token Index: 42

Text #9

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.7964. Min Act: -0.1700

Data Index: 2149178 (Open Web Text)

Max Activating Token Index: 259

Text #10

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.8093. Min Act: -0.1700

Data Index: 8595582 (Open Web Text)

Max Activating Token Index: 222

Text #11

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.8053. Min Act: -0.1700

Data Index: 1061135 (Open Web Text)

Max Activating Token Index: 902

Text #12

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.7743. Min Act: -0.1700

Data Index: 4809730 (Open Web Text)

Max Activating Token Index: 732

Text #13

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.7788. Min Act: -0.1700

Data Index: 3775386 (Open Web Text)

Max Activating Token Index: 239

Text #14

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.7599. Min Act: -0.1700

Data Index: 8569948 (Open Web Text)

Max Activating Token Index: 363

Text #15

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.7411. Min Act: -0.1700

Data Index: 1245601 (Open Web Text)

Max Activating Token Index: 435

Text #16

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.7188. Min Act: -0.1700

Data Index: 528577 (Open Web Text)

Max Activating Token Index: 681

Text #17

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.7557. Min Act: -0.1700

Data Index: 6266388 (Open Web Text)

Max Activating Token Index: 772

Text #18

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.7381. Min Act: -0.1700

Data Index: 6461028 (Open Web Text)

Max Activating Token Index: 754

Text #19

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.7349. Min Act: -0.1700

Data Index: 1235081 (Open Web Text)

Max Activating Token Index: 610