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

Dataset: Open Web Text

Neuron 861 in Layer 3

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: 4.4401. Min Range: -4.4401

Max Act: 4.4401. Min Act: -0.1700

Data Index: 3402077 (Open Web Text)

Max Activating Token Index: 772

Text #1

Max Range: 4.4401. Min Range: -4.4401

Max Act: 4.3497. Min Act: -0.1700

Data Index: 1058736 (Open Web Text)

Max Activating Token Index: 502

Text #2

Max Range: 4.4401. Min Range: -4.4401

Max Act: 4.4116. Min Act: -0.1700

Data Index: 5162820 (Open Web Text)

Max Activating Token Index: 923

Text #3

Max Range: 4.4401. Min Range: -4.4401

Max Act: 4.3492. Min Act: -0.1700

Data Index: 4199009 (Open Web Text)

Max Activating Token Index: 949

Text #4

Max Range: 4.4401. Min Range: -4.4401

Max Act: 4.3259. Min Act: -0.1700

Data Index: 359878 (Open Web Text)

Max Activating Token Index: 778

Text #5

Max Range: 4.4401. Min Range: -4.4401

Max Act: 4.3377. Min Act: -0.1700

Data Index: 5951511 (Open Web Text)

Max Activating Token Index: 447

Text #6

Max Range: 4.4401. Min Range: -4.4401

Max Act: 4.3309. Min Act: -0.1700

Data Index: 7821719 (Open Web Text)

Max Activating Token Index: 247

Text #7

Max Range: 4.4401. Min Range: -4.4401

Max Act: 4.3359. Min Act: -0.1700

Data Index: 6858948 (Open Web Text)

Max Activating Token Index: 786

Text #8

Max Range: 4.4401. Min Range: -4.4401

Max Act: 4.3571. Min Act: -0.1700

Data Index: 3193833 (Open Web Text)

Max Activating Token Index: 865

Text #9

Max Range: 4.4401. Min Range: -4.4401

Max Act: 4.3147. Min Act: -0.1700

Data Index: 1347154 (Open Web Text)

Max Activating Token Index: 974

Text #10

Max Range: 4.4401. Min Range: -4.4401

Max Act: 4.3171. Min Act: -0.1700

Data Index: 5264983 (Open Web Text)

Max Activating Token Index: 429

Text #11

Max Range: 4.4401. Min Range: -4.4401

Max Act: 4.3184. Min Act: -0.1700

Data Index: 4126910 (Open Web Text)

Max Activating Token Index: 292

Text #12

Max Range: 4.4401. Min Range: -4.4401

Max Act: 4.3229. Min Act: -0.1700

Data Index: 5237610 (Open Web Text)

Max Activating Token Index: 562

Text #13

Max Range: 4.4401. Min Range: -4.4401

Max Act: 4.3114. Min Act: -0.1700

Data Index: 1022726 (Open Web Text)

Max Activating Token Index: 229

Text #14

Max Range: 4.4401. Min Range: -4.4401

Max Act: 4.2651. Min Act: -0.1700

Data Index: 6808849 (Open Web Text)

Max Activating Token Index: 441

Text #15

Max Range: 4.4401. Min Range: -4.4401

Max Act: 4.3106. Min Act: -0.1700

Data Index: 398319 (Open Web Text)

Max Activating Token Index: 491

Text #16

Max Range: 4.4401. Min Range: -4.4401

Max Act: 4.2819. Min Act: -0.1700

Data Index: 6174711 (Open Web Text)

Max Activating Token Index: 118

Text #17

Max Range: 4.4401. Min Range: -4.4401

Max Act: 4.2862. Min Act: -0.1700

Data Index: 2995370 (Open Web Text)

Max Activating Token Index: 908

Text #18

Max Range: 4.4401. Min Range: -4.4401

Max Act: 4.3324. Min Act: -0.1700

Data Index: 1433132 (Open Web Text)

Max Activating Token Index: 602

Text #19

Max Range: 4.4401. Min Range: -4.4401

Max Act: 4.2940. Min Act: -0.1700

Data Index: 8299114 (Open Web Text)

Max Activating Token Index: 256