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

Dataset: Open Web Text

Neuron 1347 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: 3.7683. Min Range: -3.7683

Max Act: 3.7683. Min Act: -0.1700

Data Index: 4077301 (Open Web Text)

Max Activating Token Index: 871

Text #1

Max Range: 3.7683. Min Range: -3.7683

Max Act: 3.6456. Min Act: -0.1700

Data Index: 4323205 (Open Web Text)

Max Activating Token Index: 703

Text #2

Max Range: 3.7683. Min Range: -3.7683

Max Act: 3.6366. Min Act: -0.1700

Data Index: 5911862 (Open Web Text)

Max Activating Token Index: 880

Text #3

Max Range: 3.7683. Min Range: -3.7683

Max Act: 3.5569. Min Act: -0.1700

Data Index: 7003985 (Open Web Text)

Max Activating Token Index: 786

Text #4

Max Range: 3.7683. Min Range: -3.7683

Max Act: 3.5719. Min Act: -0.1700

Data Index: 4884289 (Open Web Text)

Max Activating Token Index: 656

Text #5

Max Range: 3.7683. Min Range: -3.7683

Max Act: 3.5665. Min Act: -0.1700

Data Index: 738569 (Open Web Text)

Max Activating Token Index: 637

Text #6

Max Range: 3.7683. Min Range: -3.7683

Max Act: 3.4400. Min Act: -0.1700

Data Index: 150372 (Open Web Text)

Max Activating Token Index: 368

Text #7

Max Range: 3.7683. Min Range: -3.7683

Max Act: 3.5310. Min Act: -0.1700

Data Index: 9541 (Open Web Text)

Max Activating Token Index: 865

Text #8

Max Range: 3.7683. Min Range: -3.7683

Max Act: 3.5273. Min Act: -0.1700

Data Index: 8796284 (Open Web Text)

Max Activating Token Index: 866

Text #9

Max Range: 3.7683. Min Range: -3.7683

Max Act: 3.5299. Min Act: -0.1700

Data Index: 1974995 (Open Web Text)

Max Activating Token Index: 258

Text #10

Max Range: 3.7683. Min Range: -3.7683

Max Act: 3.4889. Min Act: -0.1700

Data Index: 8389165 (Open Web Text)

Max Activating Token Index: 548

Text #11

Max Range: 3.7683. Min Range: -3.7683

Max Act: 3.5103. Min Act: -0.1700

Data Index: 3347678 (Open Web Text)

Max Activating Token Index: 118

Text #12

Max Range: 3.7683. Min Range: -3.7683

Max Act: 3.4934. Min Act: -0.1700

Data Index: 4993008 (Open Web Text)

Max Activating Token Index: 458

Text #13

Max Range: 3.7683. Min Range: -3.7683

Max Act: 3.4423. Min Act: -0.1700

Data Index: 7030548 (Open Web Text)

Max Activating Token Index: 722

Text #14

Max Range: 3.7683. Min Range: -3.7683

Max Act: 3.4623. Min Act: -0.1700

Data Index: 7960019 (Open Web Text)

Max Activating Token Index: 282

Text #15

Max Range: 3.7683. Min Range: -3.7683

Max Act: 3.4501. Min Act: -0.1700

Data Index: 4332473 (Open Web Text)

Max Activating Token Index: 950

Text #16

Max Range: 3.7683. Min Range: -3.7683

Max Act: 3.4406. Min Act: -0.1700

Data Index: 5245473 (Open Web Text)

Max Activating Token Index: 64

Text #17

Max Range: 3.7683. Min Range: -3.7683

Max Act: 3.4299. Min Act: -0.1700

Data Index: 8149658 (Open Web Text)

Max Activating Token Index: 503

Text #18

Max Range: 3.7683. Min Range: -3.7683

Max Act: 3.4520. Min Act: -0.1700

Data Index: 914939 (Open Web Text)

Max Activating Token Index: 665

Text #19

Max Range: 3.7683. Min Range: -3.7683

Max Act: 3.4146. Min Act: -0.1700

Data Index: 6550159 (Open Web Text)

Max Activating Token Index: 764