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

Dataset: Open Web Text

Neuron 2489 in Layer 0

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: 2.2514. Min Range: -2.2514

Max Act: 2.2049. Min Act: -0.1700

Data Index: 2551221 (Open Web Text)

Max Activating Token Index: 1010

Text #1

Max Range: 2.2514. Min Range: -2.2514

Max Act: 2.2514. Min Act: -0.1700

Data Index: 6220584 (Open Web Text)

Max Activating Token Index: 1019

Text #2

Max Range: 2.2514. Min Range: -2.2514

Max Act: 2.2083. Min Act: -0.1700

Data Index: 7228929 (Open Web Text)

Max Activating Token Index: 1022

Text #3

Max Range: 2.2514. Min Range: -2.2514

Max Act: 2.1805. Min Act: -0.1700

Data Index: 3376741 (Open Web Text)

Max Activating Token Index: 1021

Text #4

Max Range: 2.2514. Min Range: -2.2514

Max Act: 2.1528. Min Act: -0.1700

Data Index: 2043228 (Open Web Text)

Max Activating Token Index: 1010

Text #5

Max Range: 2.2514. Min Range: -2.2514

Max Act: 2.1271. Min Act: -0.1700

Data Index: 1672925 (Open Web Text)

Max Activating Token Index: 1008

Text #6

Max Range: 2.2514. Min Range: -2.2514

Max Act: 2.1445. Min Act: -0.1700

Data Index: 3274271 (Open Web Text)

Max Activating Token Index: 1016

Text #7

Max Range: 2.2514. Min Range: -2.2514

Max Act: 2.1171. Min Act: -0.1700

Data Index: 3786577 (Open Web Text)

Max Activating Token Index: 1021

Text #8

Max Range: 2.2514. Min Range: -2.2514

Max Act: 2.1325. Min Act: -0.1700

Data Index: 6149759 (Open Web Text)

Max Activating Token Index: 1018

Text #9

Max Range: 2.2514. Min Range: -2.2514

Max Act: 2.1337. Min Act: -0.1700

Data Index: 3220013 (Open Web Text)

Max Activating Token Index: 1013

Text #10

Max Range: 2.2514. Min Range: -2.2514

Max Act: 2.0924. Min Act: -0.1700

Data Index: 7699839 (Open Web Text)

Max Activating Token Index: 1004

Text #11

Max Range: 2.2514. Min Range: -2.2514

Max Act: 2.0906. Min Act: -0.1700

Data Index: 4373104 (Open Web Text)

Max Activating Token Index: 1021

Text #12

Max Range: 2.2514. Min Range: -2.2514

Max Act: 2.0510. Min Act: -0.1700

Data Index: 2141260 (Open Web Text)

Max Activating Token Index: 1015

Text #13

Max Range: 2.2514. Min Range: -2.2514

Max Act: 2.0844. Min Act: -0.1700

Data Index: 5532728 (Open Web Text)

Max Activating Token Index: 1010

Text #14

Max Range: 2.2514. Min Range: -2.2514

Max Act: 2.0504. Min Act: -0.1700

Data Index: 3668619 (Open Web Text)

Max Activating Token Index: 1011

Text #15

Max Range: 2.2514. Min Range: -2.2514

Max Act: 2.0688. Min Act: -0.1700

Data Index: 8139582 (Open Web Text)

Max Activating Token Index: 1021

Text #16

Max Range: 2.2514. Min Range: -2.2514

Max Act: 2.0512. Min Act: -0.1700

Data Index: 2342263 (Open Web Text)

Max Activating Token Index: 1022

Text #17

Max Range: 2.2514. Min Range: -2.2514

Max Act: 2.0582. Min Act: -0.1700

Data Index: 2048278 (Open Web Text)

Max Activating Token Index: 1016

Text #18

Max Range: 2.2514. Min Range: -2.2514

Max Act: 2.0421. Min Act: -0.1700

Data Index: 3777419 (Open Web Text)

Max Activating Token Index: 1003

Text #19

Max Range: 2.2514. Min Range: -2.2514

Max Act: 2.0394. Min Act: -0.1700

Data Index: 2029207 (Open Web Text)

Max Activating Token Index: 1016