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

Dataset: Open Web Text

Neuron 2192 in Layer 1

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: 3.5310. Min Range: -3.5310

Max Act: 3.5310. Min Act: -0.1700

Data Index: 1576782 (Open Web Text)

Max Activating Token Index: 60

Text #1

Max Range: 3.5310. Min Range: -3.5310

Max Act: 3.5012. Min Act: -0.1700

Data Index: 118416 (Open Web Text)

Max Activating Token Index: 892

Text #2

Max Range: 3.5310. Min Range: -3.5310

Max Act: 3.4857. Min Act: -0.1700

Data Index: 3602851 (Open Web Text)

Max Activating Token Index: 205

Text #3

Max Range: 3.5310. Min Range: -3.5310

Max Act: 3.4846. Min Act: -0.1700

Data Index: 109817 (Open Web Text)

Max Activating Token Index: 864

Text #4

Max Range: 3.5310. Min Range: -3.5310

Max Act: 3.4591. Min Act: -0.1700

Data Index: 8810519 (Open Web Text)

Max Activating Token Index: 888

Text #5

Max Range: 3.5310. Min Range: -3.5310

Max Act: 3.4376. Min Act: -0.1700

Data Index: 1740186 (Open Web Text)

Max Activating Token Index: 82

Text #6

Max Range: 3.5310. Min Range: -3.5310

Max Act: 3.4247. Min Act: -0.1700

Data Index: 447098 (Open Web Text)

Max Activating Token Index: 305

Text #7

Max Range: 3.5310. Min Range: -3.5310

Max Act: 3.3982. Min Act: -0.1700

Data Index: 3891991 (Open Web Text)

Max Activating Token Index: 536

Text #8

Max Range: 3.5310. Min Range: -3.5310

Max Act: 3.4056. Min Act: -0.1700

Data Index: 4653240 (Open Web Text)

Max Activating Token Index: 143

Text #9

Max Range: 3.5310. Min Range: -3.5310

Max Act: 3.3626. Min Act: -0.1700

Data Index: 3565436 (Open Web Text)

Max Activating Token Index: 545

Text #10

Max Range: 3.5310. Min Range: -3.5310

Max Act: 3.3636. Min Act: -0.1700

Data Index: 5136107 (Open Web Text)

Max Activating Token Index: 562

Text #11

Max Range: 3.5310. Min Range: -3.5310

Max Act: 3.3545. Min Act: -0.1700

Data Index: 5995807 (Open Web Text)

Max Activating Token Index: 105

Text #12

Max Range: 3.5310. Min Range: -3.5310

Max Act: 3.3469. Min Act: -0.1700

Data Index: 1258462 (Open Web Text)

Max Activating Token Index: 688

Text #13

Max Range: 3.5310. Min Range: -3.5310

Max Act: 3.3075. Min Act: -0.1700

Data Index: 1134507 (Open Web Text)

Max Activating Token Index: 91

Text #14

Max Range: 3.5310. Min Range: -3.5310

Max Act: 3.2932. Min Act: -0.1700

Data Index: 3754615 (Open Web Text)

Max Activating Token Index: 564

Text #15

Max Range: 3.5310. Min Range: -3.5310

Max Act: 3.2778. Min Act: -0.1700

Data Index: 7527688 (Open Web Text)

Max Activating Token Index: 1001

Text #16

Max Range: 3.5310. Min Range: -3.5310

Max Act: 3.2675. Min Act: -0.1700

Data Index: 3663511 (Open Web Text)

Max Activating Token Index: 811

Text #17

Max Range: 3.5310. Min Range: -3.5310

Max Act: 3.2789. Min Act: -0.1700

Data Index: 2432875 (Open Web Text)

Max Activating Token Index: 567

Text #18

Max Range: 3.5310. Min Range: -3.5310

Max Act: 3.2466. Min Act: -0.1700

Data Index: 2590285 (Open Web Text)

Max Activating Token Index: 233

Text #19

Max Range: 3.5310. Min Range: -3.5310

Max Act: 3.2670. Min Act: -0.1700

Data Index: 2222278 (Open Web Text)

Max Activating Token Index: 103