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

Dataset: Open Web Text

Neuron 1505 in Layer 6

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: 4.5845. Min Range: -4.5845

Max Act: 4.5845. Min Act: -0.1700

Data Index: 3780837 (Open Web Text)

Max Activating Token Index: 630

Text #1

Max Range: 4.5845. Min Range: -4.5845

Max Act: 4.5721. Min Act: -0.1700

Data Index: 5572222 (Open Web Text)

Max Activating Token Index: 348

Text #2

Max Range: 4.5845. Min Range: -4.5845

Max Act: 4.5706. Min Act: -0.1700

Data Index: 1031298 (Open Web Text)

Max Activating Token Index: 684

Text #3

Max Range: 4.5845. Min Range: -4.5845

Max Act: 4.5159. Min Act: -0.1700

Data Index: 3236172 (Open Web Text)

Max Activating Token Index: 270

Text #4

Max Range: 4.5845. Min Range: -4.5845

Max Act: 4.4519. Min Act: -0.1700

Data Index: 4521907 (Open Web Text)

Max Activating Token Index: 569

Text #5

Max Range: 4.5845. Min Range: -4.5845

Max Act: 4.4560. Min Act: -0.1700

Data Index: 4591898 (Open Web Text)

Max Activating Token Index: 442

Text #6

Max Range: 4.5845. Min Range: -4.5845

Max Act: 4.4020. Min Act: -0.1700

Data Index: 1978700 (Open Web Text)

Max Activating Token Index: 1013

Text #7

Max Range: 4.5845. Min Range: -4.5845

Max Act: 4.3925. Min Act: -0.1700

Data Index: 3753338 (Open Web Text)

Max Activating Token Index: 314

Text #8

Max Range: 4.5845. Min Range: -4.5845

Max Act: 4.4287. Min Act: -0.1700

Data Index: 7363509 (Open Web Text)

Max Activating Token Index: 1013

Text #9

Max Range: 4.5845. Min Range: -4.5845

Max Act: 4.4112. Min Act: -0.1700

Data Index: 1153558 (Open Web Text)

Max Activating Token Index: 842

Text #10

Max Range: 4.5845. Min Range: -4.5845

Max Act: 4.4227. Min Act: -0.1700

Data Index: 4628809 (Open Web Text)

Max Activating Token Index: 804

Text #11

Max Range: 4.5845. Min Range: -4.5845

Max Act: 4.3906. Min Act: -0.1700

Data Index: 7176229 (Open Web Text)

Max Activating Token Index: 563

Text #12

Max Range: 4.5845. Min Range: -4.5845

Max Act: 4.4004. Min Act: -0.1700

Data Index: 4010560 (Open Web Text)

Max Activating Token Index: 565

Text #13

Max Range: 4.5845. Min Range: -4.5845

Max Act: 4.3815. Min Act: -0.1700

Data Index: 1987001 (Open Web Text)

Max Activating Token Index: 869

Text #14

Max Range: 4.5845. Min Range: -4.5845

Max Act: 4.3726. Min Act: -0.1700

Data Index: 1793669 (Open Web Text)

Max Activating Token Index: 669

Text #15

Max Range: 4.5845. Min Range: -4.5845

Max Act: 4.3789. Min Act: -0.1700

Data Index: 7049992 (Open Web Text)

Max Activating Token Index: 201

Text #16

Max Range: 4.5845. Min Range: -4.5845

Max Act: 4.3922. Min Act: -0.1700

Data Index: 7522888 (Open Web Text)

Max Activating Token Index: 554

Text #17

Max Range: 4.5845. Min Range: -4.5845

Max Act: 4.3826. Min Act: -0.1700

Data Index: 1787539 (Open Web Text)

Max Activating Token Index: 819

Text #18

Max Range: 4.5845. Min Range: -4.5845

Max Act: 4.3461. Min Act: -0.1700

Data Index: 5357059 (Open Web Text)

Max Activating Token Index: 375

Text #19

Max Range: 4.5845. Min Range: -4.5845

Max Act: 4.3419. Min Act: -0.1700

Data Index: 5760105 (Open Web Text)

Max Activating Token Index: 156