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

Dataset: Open Web Text

Neuron 154 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: 1.8225. Min Range: -1.8225

Max Act: 1.8225. Min Act: -0.1700

Data Index: 3322594 (Open Web Text)

Max Activating Token Index: 247

Text #1

Max Range: 1.8225. Min Range: -1.8225

Max Act: 1.8085. Min Act: -0.1700

Data Index: 8266406 (Open Web Text)

Max Activating Token Index: 152

Text #2

Max Range: 1.8225. Min Range: -1.8225

Max Act: 1.7916. Min Act: -0.1700

Data Index: 1892718 (Open Web Text)

Max Activating Token Index: 95

Text #3

Max Range: 1.8225. Min Range: -1.8225

Max Act: 1.7733. Min Act: -0.1700

Data Index: 4355422 (Open Web Text)

Max Activating Token Index: 1002

Text #4

Max Range: 1.8225. Min Range: -1.8225

Max Act: 1.7929. Min Act: -0.1700

Data Index: 7083911 (Open Web Text)

Max Activating Token Index: 1022

Text #5

Max Range: 1.8225. Min Range: -1.8225

Max Act: 1.7559. Min Act: -0.1700

Data Index: 5315305 (Open Web Text)

Max Activating Token Index: 928

Text #6

Max Range: 1.8225. Min Range: -1.8225

Max Act: 1.7532. Min Act: -0.1700

Data Index: 2254181 (Open Web Text)

Max Activating Token Index: 190

Text #7

Max Range: 1.8225. Min Range: -1.8225

Max Act: 1.7619. Min Act: -0.1700

Data Index: 7903364 (Open Web Text)

Max Activating Token Index: 745

Text #8

Max Range: 1.8225. Min Range: -1.8225

Max Act: 1.7595. Min Act: -0.1700

Data Index: 2492968 (Open Web Text)

Max Activating Token Index: 672

Text #9

Max Range: 1.8225. Min Range: -1.8225

Max Act: 1.7355. Min Act: -0.1700

Data Index: 5417177 (Open Web Text)

Max Activating Token Index: 904

Text #10

Max Range: 1.8225. Min Range: -1.8225

Max Act: 1.7360. Min Act: -0.1700

Data Index: 2914342 (Open Web Text)

Max Activating Token Index: 634

Text #11

Max Range: 1.8225. Min Range: -1.8225

Max Act: 1.7411. Min Act: -0.1700

Data Index: 2392539 (Open Web Text)

Max Activating Token Index: 699

Text #12

Max Range: 1.8225. Min Range: -1.8225

Max Act: 1.7461. Min Act: -0.1700

Data Index: 8682846 (Open Web Text)

Max Activating Token Index: 377

Text #13

Max Range: 1.8225. Min Range: -1.8225

Max Act: 1.7383. Min Act: -0.1700

Data Index: 4140644 (Open Web Text)

Max Activating Token Index: 392

Text #14

Max Range: 1.8225. Min Range: -1.8225

Max Act: 1.7363. Min Act: -0.1700

Data Index: 3799857 (Open Web Text)

Max Activating Token Index: 112

Text #15

Max Range: 1.8225. Min Range: -1.8225

Max Act: 1.7333. Min Act: -0.1700

Data Index: 1833005 (Open Web Text)

Max Activating Token Index: 815

Text #16

Max Range: 1.8225. Min Range: -1.8225

Max Act: 1.7238. Min Act: -0.1700

Data Index: 1553523 (Open Web Text)

Max Activating Token Index: 513

Text #17

Max Range: 1.8225. Min Range: -1.8225

Max Act: 1.7316. Min Act: -0.1700

Data Index: 2073871 (Open Web Text)

Max Activating Token Index: 323

Text #18

Max Range: 1.8225. Min Range: -1.8225

Max Act: 1.7267. Min Act: -0.1700

Data Index: 5149603 (Open Web Text)

Max Activating Token Index: 640

Text #19

Max Range: 1.8225. Min Range: -1.8225

Max Act: 1.7277. Min Act: -0.1700

Data Index: 2087698 (Open Web Text)

Max Activating Token Index: 589