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

Dataset: Open Web Text

Neuron 2179 in Layer 2

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: 5.5626. Min Range: -5.5626

Max Act: 5.5626. Min Act: -0.1700

Data Index: 2137096 (Open Web Text)

Max Activating Token Index: 372

Text #1

Max Range: 5.5626. Min Range: -5.5626

Max Act: 5.5242. Min Act: -0.1700

Data Index: 3228577 (Open Web Text)

Max Activating Token Index: 879

Text #2

Max Range: 5.5626. Min Range: -5.5626

Max Act: 5.4895. Min Act: -0.1700

Data Index: 1181671 (Open Web Text)

Max Activating Token Index: 1004

Text #3

Max Range: 5.5626. Min Range: -5.5626

Max Act: 5.4630. Min Act: -0.1700

Data Index: 1293050 (Open Web Text)

Max Activating Token Index: 1011

Text #4

Max Range: 5.5626. Min Range: -5.5626

Max Act: 5.4380. Min Act: -0.1700

Data Index: 3030300 (Open Web Text)

Max Activating Token Index: 315

Text #5

Max Range: 5.5626. Min Range: -5.5626

Max Act: 5.4553. Min Act: -0.1700

Data Index: 3485639 (Open Web Text)

Max Activating Token Index: 466

Text #6

Max Range: 5.5626. Min Range: -5.5626

Max Act: 5.4195. Min Act: -0.1700

Data Index: 2329524 (Open Web Text)

Max Activating Token Index: 149

Text #7

Max Range: 5.5626. Min Range: -5.5626

Max Act: 5.4145. Min Act: -0.1700

Data Index: 6436910 (Open Web Text)

Max Activating Token Index: 982

Text #8

Max Range: 5.5626. Min Range: -5.5626

Max Act: 5.4335. Min Act: -0.1700

Data Index: 1425585 (Open Web Text)

Max Activating Token Index: 462

Text #9

Max Range: 5.5626. Min Range: -5.5626

Max Act: 5.4219. Min Act: -0.1700

Data Index: 3657580 (Open Web Text)

Max Activating Token Index: 686

Text #10

Max Range: 5.5626. Min Range: -5.5626

Max Act: 5.3882. Min Act: -0.1700

Data Index: 6229926 (Open Web Text)

Max Activating Token Index: 593

Text #11

Max Range: 5.5626. Min Range: -5.5626

Max Act: 5.3821. Min Act: -0.1700

Data Index: 2960786 (Open Web Text)

Max Activating Token Index: 740

Text #12

Max Range: 5.5626. Min Range: -5.5626

Max Act: 5.3805. Min Act: -0.1700

Data Index: 446897 (Open Web Text)

Max Activating Token Index: 791

Text #13

Max Range: 5.5626. Min Range: -5.5626

Max Act: 5.3883. Min Act: -0.1700

Data Index: 5325122 (Open Web Text)

Max Activating Token Index: 79

Text #14

Max Range: 5.5626. Min Range: -5.5626

Max Act: 5.3712. Min Act: -0.1700

Data Index: 4124716 (Open Web Text)

Max Activating Token Index: 146

Text #15

Max Range: 5.5626. Min Range: -5.5626

Max Act: 5.3567. Min Act: -0.1700

Data Index: 4015749 (Open Web Text)

Max Activating Token Index: 597

Text #16

Max Range: 5.5626. Min Range: -5.5626

Max Act: 5.3698. Min Act: -0.1700

Data Index: 204426 (Open Web Text)

Max Activating Token Index: 629

Text #17

Max Range: 5.5626. Min Range: -5.5626

Max Act: 5.3740. Min Act: -0.1700

Data Index: 3842997 (Open Web Text)

Max Activating Token Index: 220

Text #18

Max Range: 5.5626. Min Range: -5.5626

Max Act: 5.3036. Min Act: -0.1700

Data Index: 1574149 (Open Web Text)

Max Activating Token Index: 225

Text #19

Max Range: 5.5626. Min Range: -5.5626

Max Act: 5.3368. Min Act: -0.1700

Data Index: 1529412 (Open Web Text)

Max Activating Token Index: 648