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

Dataset: Open Web Text

Neuron 637 in Layer 5

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: 6.4656. Min Range: -6.4656

Max Act: 6.4656. Min Act: -0.1700

Data Index: 4249938 (Open Web Text)

Max Activating Token Index: 706

Text #1

Max Range: 6.4656. Min Range: -6.4656

Max Act: 6.3724. Min Act: -0.1700

Data Index: 8212043 (Open Web Text)

Max Activating Token Index: 544

Text #2

Max Range: 6.4656. Min Range: -6.4656

Max Act: 6.3324. Min Act: -0.1700

Data Index: 8048967 (Open Web Text)

Max Activating Token Index: 541

Text #3

Max Range: 6.4656. Min Range: -6.4656

Max Act: 6.2322. Min Act: -0.1700

Data Index: 1934271 (Open Web Text)

Max Activating Token Index: 41

Text #4

Max Range: 6.4656. Min Range: -6.4656

Max Act: 6.1334. Min Act: -0.1700

Data Index: 621141 (Open Web Text)

Max Activating Token Index: 763

Text #5

Max Range: 6.4656. Min Range: -6.4656

Max Act: 6.1328. Min Act: -0.1700

Data Index: 1697221 (Open Web Text)

Max Activating Token Index: 645

Text #6

Max Range: 6.4656. Min Range: -6.4656

Max Act: 6.0655. Min Act: -0.1700

Data Index: 2203063 (Open Web Text)

Max Activating Token Index: 347

Text #7

Max Range: 6.4656. Min Range: -6.4656

Max Act: 6.0667. Min Act: -0.1700

Data Index: 2713149 (Open Web Text)

Max Activating Token Index: 764

Text #8

Max Range: 6.4656. Min Range: -6.4656

Max Act: 6.0241. Min Act: -0.1700

Data Index: 5535027 (Open Web Text)

Max Activating Token Index: 331

Text #9

Max Range: 6.4656. Min Range: -6.4656

Max Act: 6.0329. Min Act: -0.1700

Data Index: 3855388 (Open Web Text)

Max Activating Token Index: 396

Text #10

Max Range: 6.4656. Min Range: -6.4656

Max Act: 6.0535. Min Act: -0.1700

Data Index: 6656615 (Open Web Text)

Max Activating Token Index: 185

Text #11

Max Range: 6.4656. Min Range: -6.4656

Max Act: 6.0166. Min Act: -0.1700

Data Index: 699379 (Open Web Text)

Max Activating Token Index: 310

Text #12

Max Range: 6.4656. Min Range: -6.4656

Max Act: 6.0578. Min Act: -0.1700

Data Index: 2109166 (Open Web Text)

Max Activating Token Index: 222

Text #13

Max Range: 6.4656. Min Range: -6.4656

Max Act: 6.0161. Min Act: -0.1700

Data Index: 5860505 (Open Web Text)

Max Activating Token Index: 37

Text #14

Max Range: 6.4656. Min Range: -6.4656

Max Act: 6.0119. Min Act: -0.1700

Data Index: 6950735 (Open Web Text)

Max Activating Token Index: 544

Text #15

Max Range: 6.4656. Min Range: -6.4656

Max Act: 5.9789. Min Act: -0.1700

Data Index: 59842 (Open Web Text)

Max Activating Token Index: 517

Text #16

Max Range: 6.4656. Min Range: -6.4656

Max Act: 6.0178. Min Act: -0.1700

Data Index: 3195975 (Open Web Text)

Max Activating Token Index: 186

Text #17

Max Range: 6.4656. Min Range: -6.4656

Max Act: 5.9903. Min Act: -0.1700

Data Index: 3540872 (Open Web Text)

Max Activating Token Index: 236

Text #18

Max Range: 6.4656. Min Range: -6.4656

Max Act: 5.9728. Min Act: -0.1700

Data Index: 1479540 (Open Web Text)

Max Activating Token Index: 249

Text #19

Max Range: 6.4656. Min Range: -6.4656

Max Act: 6.0144. Min Act: -0.1700

Data Index: 6275585 (Open Web Text)

Max Activating Token Index: 170