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

Dataset: Open Web Text

Neuron 84 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: 4.2074. Min Range: -4.2074

Max Act: 4.2074. Min Act: -0.1700

Data Index: 5095894 (Open Web Text)

Max Activating Token Index: 581

Text #1

Max Range: 4.2074. Min Range: -4.2074

Max Act: 4.1901. Min Act: -0.1700

Data Index: 2175340 (Open Web Text)

Max Activating Token Index: 940

Text #2

Max Range: 4.2074. Min Range: -4.2074

Max Act: 4.1286. Min Act: -0.1700

Data Index: 5752454 (Open Web Text)

Max Activating Token Index: 131

Text #3

Max Range: 4.2074. Min Range: -4.2074

Max Act: 4.1334. Min Act: -0.1700

Data Index: 1163528 (Open Web Text)

Max Activating Token Index: 788

Text #4

Max Range: 4.2074. Min Range: -4.2074

Max Act: 4.0970. Min Act: -0.1700

Data Index: 1150240 (Open Web Text)

Max Activating Token Index: 600

Text #5

Max Range: 4.2074. Min Range: -4.2074

Max Act: 4.1041. Min Act: -0.1700

Data Index: 8802134 (Open Web Text)

Max Activating Token Index: 232

Text #6

Max Range: 4.2074. Min Range: -4.2074

Max Act: 4.1207. Min Act: -0.1700

Data Index: 5866248 (Open Web Text)

Max Activating Token Index: 195

Text #7

Max Range: 4.2074. Min Range: -4.2074

Max Act: 4.1085. Min Act: -0.1700

Data Index: 5759801 (Open Web Text)

Max Activating Token Index: 1009

Text #8

Max Range: 4.2074. Min Range: -4.2074

Max Act: 4.1074. Min Act: -0.1700

Data Index: 1344378 (Open Web Text)

Max Activating Token Index: 75

Text #9

Max Range: 4.2074. Min Range: -4.2074

Max Act: 4.1062. Min Act: -0.1700

Data Index: 5952462 (Open Web Text)

Max Activating Token Index: 493

Text #10

Max Range: 4.2074. Min Range: -4.2074

Max Act: 4.1064. Min Act: -0.1700

Data Index: 3159311 (Open Web Text)

Max Activating Token Index: 625

Text #11

Max Range: 4.2074. Min Range: -4.2074

Max Act: 4.0863. Min Act: -0.1700

Data Index: 277982 (Open Web Text)

Max Activating Token Index: 558

Text #12

Max Range: 4.2074. Min Range: -4.2074

Max Act: 4.0896. Min Act: -0.1700

Data Index: 811983 (Open Web Text)

Max Activating Token Index: 318

Text #13

Max Range: 4.2074. Min Range: -4.2074

Max Act: 4.0614. Min Act: -0.1700

Data Index: 7241348 (Open Web Text)

Max Activating Token Index: 540

Text #14

Max Range: 4.2074. Min Range: -4.2074

Max Act: 4.0744. Min Act: -0.1700

Data Index: 7578844 (Open Web Text)

Max Activating Token Index: 883

Text #15

Max Range: 4.2074. Min Range: -4.2074

Max Act: 4.0793. Min Act: -0.1700

Data Index: 8307385 (Open Web Text)

Max Activating Token Index: 300

Text #16

Max Range: 4.2074. Min Range: -4.2074

Max Act: 4.0671. Min Act: -0.1700

Data Index: 1210260 (Open Web Text)

Max Activating Token Index: 526

Text #17

Max Range: 4.2074. Min Range: -4.2074

Max Act: 4.0580. Min Act: -0.1700

Data Index: 5885402 (Open Web Text)

Max Activating Token Index: 56

Text #18

Max Range: 4.2074. Min Range: -4.2074

Max Act: 4.0504. Min Act: -0.1700

Data Index: 2149714 (Open Web Text)

Max Activating Token Index: 938

Text #19

Max Range: 4.2074. Min Range: -4.2074

Max Act: 4.0644. Min Act: -0.1700

Data Index: 6291477 (Open Web Text)

Max Activating Token Index: 951