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

Dataset: Open Web Text

Neuron 221 in Layer 5

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: 4.9097. Min Range: -4.9097

Max Act: 4.9097. Min Act: -0.1700

Data Index: 8609062 (Open Web Text)

Max Activating Token Index: 246

Text #1

Max Range: 4.9097. Min Range: -4.9097

Max Act: 4.8853. Min Act: -0.1700

Data Index: 8727855 (Open Web Text)

Max Activating Token Index: 624

Text #2

Max Range: 4.9097. Min Range: -4.9097

Max Act: 4.8569. Min Act: -0.1700

Data Index: 5738171 (Open Web Text)

Max Activating Token Index: 841

Text #3

Max Range: 4.9097. Min Range: -4.9097

Max Act: 4.8385. Min Act: -0.1700

Data Index: 2346678 (Open Web Text)

Max Activating Token Index: 765

Text #4

Max Range: 4.9097. Min Range: -4.9097

Max Act: 4.8110. Min Act: -0.1700

Data Index: 5292730 (Open Web Text)

Max Activating Token Index: 599

Text #5

Max Range: 4.9097. Min Range: -4.9097

Max Act: 4.7387. Min Act: -0.1700

Data Index: 6402211 (Open Web Text)

Max Activating Token Index: 471

Text #6

Max Range: 4.9097. Min Range: -4.9097

Max Act: 4.7287. Min Act: -0.1700

Data Index: 2284211 (Open Web Text)

Max Activating Token Index: 339

Text #7

Max Range: 4.9097. Min Range: -4.9097

Max Act: 4.7039. Min Act: -0.1700

Data Index: 6410114 (Open Web Text)

Max Activating Token Index: 696

Text #8

Max Range: 4.9097. Min Range: -4.9097

Max Act: 4.6874. Min Act: -0.1700

Data Index: 2573588 (Open Web Text)

Max Activating Token Index: 72

Text #9

Max Range: 4.9097. Min Range: -4.9097

Max Act: 4.6806. Min Act: -0.1700

Data Index: 8130763 (Open Web Text)

Max Activating Token Index: 526

Text #10

Max Range: 4.9097. Min Range: -4.9097

Max Act: 4.6560. Min Act: -0.1700

Data Index: 5073848 (Open Web Text)

Max Activating Token Index: 218

Text #11

Max Range: 4.9097. Min Range: -4.9097

Max Act: 4.6447. Min Act: -0.1700

Data Index: 6426516 (Open Web Text)

Max Activating Token Index: 775

Text #12

Max Range: 4.9097. Min Range: -4.9097

Max Act: 4.6666. Min Act: -0.1700

Data Index: 2396188 (Open Web Text)

Max Activating Token Index: 226

Text #13

Max Range: 4.9097. Min Range: -4.9097

Max Act: 4.6480. Min Act: -0.1700

Data Index: 3208130 (Open Web Text)

Max Activating Token Index: 564

Text #14

Max Range: 4.9097. Min Range: -4.9097

Max Act: 4.6594. Min Act: -0.1700

Data Index: 5266056 (Open Web Text)

Max Activating Token Index: 616

Text #15

Max Range: 4.9097. Min Range: -4.9097

Max Act: 4.6645. Min Act: -0.1700

Data Index: 2653542 (Open Web Text)

Max Activating Token Index: 348

Text #16

Max Range: 4.9097. Min Range: -4.9097

Max Act: 4.6484. Min Act: -0.1700

Data Index: 2865671 (Open Web Text)

Max Activating Token Index: 864

Text #17

Max Range: 4.9097. Min Range: -4.9097

Max Act: 4.6087. Min Act: -0.1700

Data Index: 7858942 (Open Web Text)

Max Activating Token Index: 815

Text #18

Max Range: 4.9097. Min Range: -4.9097

Max Act: 4.5741. Min Act: -0.1700

Data Index: 2821583 (Open Web Text)

Max Activating Token Index: 490

Text #19

Max Range: 4.9097. Min Range: -4.9097

Max Act: 4.5825. Min Act: -0.1700

Data Index: 901617 (Open Web Text)

Max Activating Token Index: 668