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

Dataset: Open Web Text

Neuron 2871 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: 4.0386. Min Range: -4.0386

Max Act: 4.0344. Min Act: -0.1700

Data Index: 2853677 (Open Web Text)

Max Activating Token Index: 1004

Text #1

Max Range: 4.0386. Min Range: -4.0386

Max Act: 4.0386. Min Act: -0.1700

Data Index: 5861432 (Open Web Text)

Max Activating Token Index: 478

Text #2

Max Range: 4.0386. Min Range: -4.0386

Max Act: 3.9964. Min Act: -0.1700

Data Index: 1935405 (Open Web Text)

Max Activating Token Index: 987

Text #3

Max Range: 4.0386. Min Range: -4.0386

Max Act: 4.0247. Min Act: -0.1700

Data Index: 5865684 (Open Web Text)

Max Activating Token Index: 1013

Text #4

Max Range: 4.0386. Min Range: -4.0386

Max Act: 3.9756. Min Act: -0.1700

Data Index: 4835976 (Open Web Text)

Max Activating Token Index: 197

Text #5

Max Range: 4.0386. Min Range: -4.0386

Max Act: 4.0074. Min Act: -0.1700

Data Index: 1498337 (Open Web Text)

Max Activating Token Index: 284

Text #6

Max Range: 4.0386. Min Range: -4.0386

Max Act: 4.0044. Min Act: -0.1700

Data Index: 8824011 (Open Web Text)

Max Activating Token Index: 587

Text #7

Max Range: 4.0386. Min Range: -4.0386

Max Act: 4.0048. Min Act: -0.1700

Data Index: 1334696 (Open Web Text)

Max Activating Token Index: 569

Text #8

Max Range: 4.0386. Min Range: -4.0386

Max Act: 3.9881. Min Act: -0.1700

Data Index: 7735680 (Open Web Text)

Max Activating Token Index: 265

Text #9

Max Range: 4.0386. Min Range: -4.0386

Max Act: 3.9855. Min Act: -0.1700

Data Index: 7083058 (Open Web Text)

Max Activating Token Index: 542

Text #10

Max Range: 4.0386. Min Range: -4.0386

Max Act: 3.9938. Min Act: -0.1700

Data Index: 1964748 (Open Web Text)

Max Activating Token Index: 336

Text #11

Max Range: 4.0386. Min Range: -4.0386

Max Act: 3.9790. Min Act: -0.1700

Data Index: 5439593 (Open Web Text)

Max Activating Token Index: 601

Text #12

Max Range: 4.0386. Min Range: -4.0386

Max Act: 3.9910. Min Act: -0.1700

Data Index: 4871456 (Open Web Text)

Max Activating Token Index: 1000

Text #13

Max Range: 4.0386. Min Range: -4.0386

Max Act: 3.9887. Min Act: -0.1700

Data Index: 1860598 (Open Web Text)

Max Activating Token Index: 986

Text #14

Max Range: 4.0386. Min Range: -4.0386

Max Act: 4.0108. Min Act: -0.1700

Data Index: 4241912 (Open Web Text)

Max Activating Token Index: 432

Text #15

Max Range: 4.0386. Min Range: -4.0386

Max Act: 3.9756. Min Act: -0.1700

Data Index: 2872872 (Open Web Text)

Max Activating Token Index: 724

Text #16

Max Range: 4.0386. Min Range: -4.0386

Max Act: 3.9445. Min Act: -0.1700

Data Index: 57269 (Open Web Text)

Max Activating Token Index: 992

Text #17

Max Range: 4.0386. Min Range: -4.0386

Max Act: 3.9552. Min Act: -0.1700

Data Index: 3151249 (Open Web Text)

Max Activating Token Index: 1012

Text #18

Max Range: 4.0386. Min Range: -4.0386

Max Act: 3.9664. Min Act: -0.1700

Data Index: 3306979 (Open Web Text)

Max Activating Token Index: 203

Text #19

Max Range: 4.0386. Min Range: -4.0386

Max Act: 3.9580. Min Act: -0.1700

Data Index: 3364478 (Open Web Text)

Max Activating Token Index: 600