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

Dataset: Open Web Text

Neuron 883 in Layer 2

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: 3.5854. Min Range: -3.5854

Max Act: 3.5854. Min Act: -0.1700

Data Index: 5861694 (Open Web Text)

Max Activating Token Index: 852

Text #1

Max Range: 3.5854. Min Range: -3.5854

Max Act: 3.5770. Min Act: -0.1700

Data Index: 1800269 (Open Web Text)

Max Activating Token Index: 12

Text #2

Max Range: 3.5854. Min Range: -3.5854

Max Act: 3.5521. Min Act: -0.1700

Data Index: 5046795 (Open Web Text)

Max Activating Token Index: 1009

Text #3

Max Range: 3.5854. Min Range: -3.5854

Max Act: 3.5355. Min Act: -0.1700

Data Index: 8185092 (Open Web Text)

Max Activating Token Index: 418

Text #4

Max Range: 3.5854. Min Range: -3.5854

Max Act: 3.5086. Min Act: -0.1700

Data Index: 5084314 (Open Web Text)

Max Activating Token Index: 863

Text #5

Max Range: 3.5854. Min Range: -3.5854

Max Act: 3.4726. Min Act: -0.1700

Data Index: 6843927 (Open Web Text)

Max Activating Token Index: 713

Text #6

Max Range: 3.5854. Min Range: -3.5854

Max Act: 3.4928. Min Act: -0.1700

Data Index: 5531702 (Open Web Text)

Max Activating Token Index: 264

Text #7

Max Range: 3.5854. Min Range: -3.5854

Max Act: 3.4821. Min Act: -0.1700

Data Index: 4275445 (Open Web Text)

Max Activating Token Index: 136

Text #8

Max Range: 3.5854. Min Range: -3.5854

Max Act: 3.4773. Min Act: -0.1700

Data Index: 4649908 (Open Web Text)

Max Activating Token Index: 193

Text #9

Max Range: 3.5854. Min Range: -3.5854

Max Act: 3.4881. Min Act: -0.1700

Data Index: 4756825 (Open Web Text)

Max Activating Token Index: 367

Text #10

Max Range: 3.5854. Min Range: -3.5854

Max Act: 3.4503. Min Act: -0.1700

Data Index: 8230547 (Open Web Text)

Max Activating Token Index: 446

Text #11

Max Range: 3.5854. Min Range: -3.5854

Max Act: 3.4569. Min Act: -0.1700

Data Index: 2523237 (Open Web Text)

Max Activating Token Index: 507

Text #12

Max Range: 3.5854. Min Range: -3.5854

Max Act: 3.4397. Min Act: -0.1700

Data Index: 759388 (Open Web Text)

Max Activating Token Index: 210

Text #13

Max Range: 3.5854. Min Range: -3.5854

Max Act: 3.4241. Min Act: -0.1700

Data Index: 8615957 (Open Web Text)

Max Activating Token Index: 42

Text #14

Max Range: 3.5854. Min Range: -3.5854

Max Act: 3.4474. Min Act: -0.1700

Data Index: 5273561 (Open Web Text)

Max Activating Token Index: 54

Text #15

Max Range: 3.5854. Min Range: -3.5854

Max Act: 3.4168. Min Act: -0.1700

Data Index: 717003 (Open Web Text)

Max Activating Token Index: 28

Text #16

Max Range: 3.5854. Min Range: -3.5854

Max Act: 3.3974. Min Act: -0.1700

Data Index: 4184339 (Open Web Text)

Max Activating Token Index: 849

Text #17

Max Range: 3.5854. Min Range: -3.5854

Max Act: 3.4369. Min Act: -0.1700

Data Index: 883865 (Open Web Text)

Max Activating Token Index: 929

Text #18

Max Range: 3.5854. Min Range: -3.5854

Max Act: 3.3960. Min Act: -0.1700

Data Index: 1715241 (Open Web Text)

Max Activating Token Index: 168

Text #19

Max Range: 3.5854. Min Range: -3.5854

Max Act: 3.4095. Min Act: -0.1700

Data Index: 41103 (Open Web Text)

Max Activating Token Index: 50