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

Dataset: Open Web Text

Neuron 3061 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: 5.2248. Min Range: -5.2248

Max Act: 5.2248. Min Act: -0.1700

Data Index: 4857434 (Open Web Text)

Max Activating Token Index: 869

Text #1

Max Range: 5.2248. Min Range: -5.2248

Max Act: 5.1918. Min Act: -0.1700

Data Index: 3717759 (Open Web Text)

Max Activating Token Index: 505

Text #2

Max Range: 5.2248. Min Range: -5.2248

Max Act: 5.0745. Min Act: -0.1700

Data Index: 180851 (Open Web Text)

Max Activating Token Index: 288

Text #3

Max Range: 5.2248. Min Range: -5.2248

Max Act: 5.0274. Min Act: -0.1700

Data Index: 926205 (Open Web Text)

Max Activating Token Index: 106

Text #4

Max Range: 5.2248. Min Range: -5.2248

Max Act: 5.0304. Min Act: -0.1700

Data Index: 7948951 (Open Web Text)

Max Activating Token Index: 763

Text #5

Max Range: 5.2248. Min Range: -5.2248

Max Act: 5.0278. Min Act: -0.1700

Data Index: 6785180 (Open Web Text)

Max Activating Token Index: 97

Text #6

Max Range: 5.2248. Min Range: -5.2248

Max Act: 4.9719. Min Act: -0.1700

Data Index: 8309917 (Open Web Text)

Max Activating Token Index: 878

Text #7

Max Range: 5.2248. Min Range: -5.2248

Max Act: 4.9775. Min Act: -0.1700

Data Index: 4946731 (Open Web Text)

Max Activating Token Index: 583

Text #8

Max Range: 5.2248. Min Range: -5.2248

Max Act: 4.9891. Min Act: -0.1700

Data Index: 5938420 (Open Web Text)

Max Activating Token Index: 591

Text #9

Max Range: 5.2248. Min Range: -5.2248

Max Act: 4.9856. Min Act: -0.1700

Data Index: 3761093 (Open Web Text)

Max Activating Token Index: 621

Text #10

Max Range: 5.2248. Min Range: -5.2248

Max Act: 4.9629. Min Act: -0.1700

Data Index: 2185688 (Open Web Text)

Max Activating Token Index: 524

Text #11

Max Range: 5.2248. Min Range: -5.2248

Max Act: 4.9900. Min Act: -0.1700

Data Index: 2166466 (Open Web Text)

Max Activating Token Index: 293

Text #12

Max Range: 5.2248. Min Range: -5.2248

Max Act: 4.9321. Min Act: -0.1700

Data Index: 3390014 (Open Web Text)

Max Activating Token Index: 106

Text #13

Max Range: 5.2248. Min Range: -5.2248

Max Act: 4.9672. Min Act: -0.1700

Data Index: 2283939 (Open Web Text)

Max Activating Token Index: 407

Text #14

Max Range: 5.2248. Min Range: -5.2248

Max Act: 4.9445. Min Act: -0.1700

Data Index: 4952866 (Open Web Text)

Max Activating Token Index: 524

Text #15

Max Range: 5.2248. Min Range: -5.2248

Max Act: 4.9279. Min Act: -0.1700

Data Index: 4739690 (Open Web Text)

Max Activating Token Index: 232

Text #16

Max Range: 5.2248. Min Range: -5.2248

Max Act: 4.9209. Min Act: -0.1700

Data Index: 4261011 (Open Web Text)

Max Activating Token Index: 109

Text #17

Max Range: 5.2248. Min Range: -5.2248

Max Act: 4.9117. Min Act: -0.1700

Data Index: 2321451 (Open Web Text)

Max Activating Token Index: 363

Text #18

Max Range: 5.2248. Min Range: -5.2248

Max Act: 4.9123. Min Act: -0.1700

Data Index: 3615720 (Open Web Text)

Max Activating Token Index: 225

Text #19

Max Range: 5.2248. Min Range: -5.2248

Max Act: 4.9081. Min Act: -0.1700

Data Index: 4996415 (Open Web Text)

Max Activating Token Index: 37