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

Dataset: Open Web Text

Neuron 296 in Layer 3

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: 4.6278. Min Range: -4.6278

Max Act: 4.6278. Min Act: -0.1700

Data Index: 7249874 (Open Web Text)

Max Activating Token Index: 307

Text #1

Max Range: 4.6278. Min Range: -4.6278

Max Act: 4.3885. Min Act: -0.1700

Data Index: 7777531 (Open Web Text)

Max Activating Token Index: 24

Text #2

Max Range: 4.6278. Min Range: -4.6278

Max Act: 4.3837. Min Act: -0.1700

Data Index: 7057890 (Open Web Text)

Max Activating Token Index: 873

Text #3

Max Range: 4.6278. Min Range: -4.6278

Max Act: 4.3256. Min Act: -0.1700

Data Index: 3182782 (Open Web Text)

Max Activating Token Index: 977

Text #4

Max Range: 4.6278. Min Range: -4.6278

Max Act: 4.3115. Min Act: -0.1700

Data Index: 7136524 (Open Web Text)

Max Activating Token Index: 1011

Text #5

Max Range: 4.6278. Min Range: -4.6278

Max Act: 4.2747. Min Act: -0.1700

Data Index: 7510980 (Open Web Text)

Max Activating Token Index: 801

Text #6

Max Range: 4.6278. Min Range: -4.6278

Max Act: 4.2866. Min Act: -0.1700

Data Index: 3526610 (Open Web Text)

Max Activating Token Index: 969

Text #7

Max Range: 4.6278. Min Range: -4.6278

Max Act: 4.2899. Min Act: -0.1700

Data Index: 5215319 (Open Web Text)

Max Activating Token Index: 576

Text #8

Max Range: 4.6278. Min Range: -4.6278

Max Act: 4.2573. Min Act: -0.1700

Data Index: 5981325 (Open Web Text)

Max Activating Token Index: 944

Text #9

Max Range: 4.6278. Min Range: -4.6278

Max Act: 4.2157. Min Act: -0.1700

Data Index: 4180747 (Open Web Text)

Max Activating Token Index: 481

Text #10

Max Range: 4.6278. Min Range: -4.6278

Max Act: 4.2293. Min Act: -0.1700

Data Index: 3879489 (Open Web Text)

Max Activating Token Index: 823

Text #11

Max Range: 4.6278. Min Range: -4.6278

Max Act: 4.2273. Min Act: -0.1700

Data Index: 4718137 (Open Web Text)

Max Activating Token Index: 728

Text #12

Max Range: 4.6278. Min Range: -4.6278

Max Act: 4.2594. Min Act: -0.1700

Data Index: 7761371 (Open Web Text)

Max Activating Token Index: 608

Text #13

Max Range: 4.6278. Min Range: -4.6278

Max Act: 4.2319. Min Act: -0.1700

Data Index: 4108035 (Open Web Text)

Max Activating Token Index: 77

Text #14

Max Range: 4.6278. Min Range: -4.6278

Max Act: 4.2284. Min Act: -0.1700

Data Index: 3414904 (Open Web Text)

Max Activating Token Index: 617

Text #15

Max Range: 4.6278. Min Range: -4.6278

Max Act: 4.2106. Min Act: -0.1700

Data Index: 5610858 (Open Web Text)

Max Activating Token Index: 216

Text #16

Max Range: 4.6278. Min Range: -4.6278

Max Act: 4.1655. Min Act: -0.1700

Data Index: 6986388 (Open Web Text)

Max Activating Token Index: 117

Text #17

Max Range: 4.6278. Min Range: -4.6278

Max Act: 4.1953. Min Act: -0.1700

Data Index: 174842 (Open Web Text)

Max Activating Token Index: 307

Text #18

Max Range: 4.6278. Min Range: -4.6278

Max Act: 4.2411. Min Act: -0.1700

Data Index: 3715751 (Open Web Text)

Max Activating Token Index: 750

Text #19

Max Range: 4.6278. Min Range: -4.6278

Max Act: 4.1896. Min Act: -0.1700

Data Index: 2818013 (Open Web Text)

Max Activating Token Index: 833