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

Dataset: Open Web Text

Neuron 633 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: 3.0545. Min Range: -3.0545

Max Act: 3.0545. Min Act: -0.1700

Data Index: 4512358 (Open Web Text)

Max Activating Token Index: 252

Text #1

Max Range: 3.0545. Min Range: -3.0545

Max Act: 2.9079. Min Act: -0.1700

Data Index: 5451466 (Open Web Text)

Max Activating Token Index: 359

Text #2

Max Range: 3.0545. Min Range: -3.0545

Max Act: 2.9019. Min Act: -0.1700

Data Index: 5632325 (Open Web Text)

Max Activating Token Index: 676

Text #3

Max Range: 3.0545. Min Range: -3.0545

Max Act: 2.8633. Min Act: -0.1700

Data Index: 180515 (Open Web Text)

Max Activating Token Index: 241

Text #4

Max Range: 3.0545. Min Range: -3.0545

Max Act: 2.8518. Min Act: -0.1700

Data Index: 5337613 (Open Web Text)

Max Activating Token Index: 184

Text #5

Max Range: 3.0545. Min Range: -3.0545

Max Act: 2.8425. Min Act: -0.1700

Data Index: 5271456 (Open Web Text)

Max Activating Token Index: 134

Text #6

Max Range: 3.0545. Min Range: -3.0545

Max Act: 2.8066. Min Act: -0.1700

Data Index: 3603172 (Open Web Text)

Max Activating Token Index: 415

Text #7

Max Range: 3.0545. Min Range: -3.0545

Max Act: 2.8186. Min Act: -0.1700

Data Index: 8018672 (Open Web Text)

Max Activating Token Index: 142

Text #8

Max Range: 3.0545. Min Range: -3.0545

Max Act: 2.7784. Min Act: -0.1700

Data Index: 8175593 (Open Web Text)

Max Activating Token Index: 44

Text #9

Max Range: 3.0545. Min Range: -3.0545

Max Act: 2.7781. Min Act: -0.1700

Data Index: 4610271 (Open Web Text)

Max Activating Token Index: 726

Text #10

Max Range: 3.0545. Min Range: -3.0545

Max Act: 2.7814. Min Act: -0.1700

Data Index: 1702324 (Open Web Text)

Max Activating Token Index: 86

Text #11

Max Range: 3.0545. Min Range: -3.0545

Max Act: 2.7841. Min Act: -0.1700

Data Index: 1368561 (Open Web Text)

Max Activating Token Index: 31

Text #12

Max Range: 3.0545. Min Range: -3.0545

Max Act: 2.7810. Min Act: -0.1700

Data Index: 2337725 (Open Web Text)

Max Activating Token Index: 536

Text #13

Max Range: 3.0545. Min Range: -3.0545

Max Act: 2.7855. Min Act: -0.1700

Data Index: 6010216 (Open Web Text)

Max Activating Token Index: 646

Text #14

Max Range: 3.0545. Min Range: -3.0545

Max Act: 2.7687. Min Act: -0.1700

Data Index: 2673417 (Open Web Text)

Max Activating Token Index: 705

Text #15

Max Range: 3.0545. Min Range: -3.0545

Max Act: 2.7827. Min Act: -0.1700

Data Index: 4368380 (Open Web Text)

Max Activating Token Index: 126

Text #16

Max Range: 3.0545. Min Range: -3.0545

Max Act: 2.7796. Min Act: -0.1700

Data Index: 6578016 (Open Web Text)

Max Activating Token Index: 747

Text #17

Max Range: 3.0545. Min Range: -3.0545

Max Act: 2.7611. Min Act: -0.1700

Data Index: 711424 (Open Web Text)

Max Activating Token Index: 870

Text #18

Max Range: 3.0545. Min Range: -3.0545

Max Act: 2.7777. Min Act: -0.1700

Data Index: 1395679 (Open Web Text)

Max Activating Token Index: 255

Text #19

Max Range: 3.0545. Min Range: -3.0545

Max Act: 2.7561. Min Act: -0.1700

Data Index: 447264 (Open Web Text)

Max Activating Token Index: 325