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

Dataset: Open Web Text

Neuron 316 in Layer 4

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: 3.3593. Min Range: -3.3593

Max Act: 3.3593. Min Act: -0.1700

Data Index: 2801936 (Open Web Text)

Max Activating Token Index: 332

Text #1

Max Range: 3.3593. Min Range: -3.3593

Max Act: 3.3094. Min Act: -0.1700

Data Index: 366108 (Open Web Text)

Max Activating Token Index: 258

Text #2

Max Range: 3.3593. Min Range: -3.3593

Max Act: 3.3416. Min Act: -0.1700

Data Index: 2350738 (Open Web Text)

Max Activating Token Index: 316

Text #3

Max Range: 3.3593. Min Range: -3.3593

Max Act: 3.3115. Min Act: -0.1700

Data Index: 3934492 (Open Web Text)

Max Activating Token Index: 527

Text #4

Max Range: 3.3593. Min Range: -3.3593

Max Act: 3.2787. Min Act: -0.1700

Data Index: 3413484 (Open Web Text)

Max Activating Token Index: 221

Text #5

Max Range: 3.3593. Min Range: -3.3593

Max Act: 3.2199. Min Act: -0.1700

Data Index: 3030333 (Open Web Text)

Max Activating Token Index: 223

Text #6

Max Range: 3.3593. Min Range: -3.3593

Max Act: 3.2320. Min Act: -0.1700

Data Index: 5760385 (Open Web Text)

Max Activating Token Index: 912

Text #7

Max Range: 3.3593. Min Range: -3.3593

Max Act: 3.1979. Min Act: -0.1700

Data Index: 3712423 (Open Web Text)

Max Activating Token Index: 944

Text #8

Max Range: 3.3593. Min Range: -3.3593

Max Act: 3.1927. Min Act: -0.1700

Data Index: 5596214 (Open Web Text)

Max Activating Token Index: 309

Text #9

Max Range: 3.3593. Min Range: -3.3593

Max Act: 3.1752. Min Act: -0.1700

Data Index: 8118468 (Open Web Text)

Max Activating Token Index: 926

Text #10

Max Range: 3.3593. Min Range: -3.3593

Max Act: 3.1354. Min Act: -0.1700

Data Index: 6821399 (Open Web Text)

Max Activating Token Index: 151

Text #11

Max Range: 3.3593. Min Range: -3.3593

Max Act: 3.1911. Min Act: -0.1700

Data Index: 2299900 (Open Web Text)

Max Activating Token Index: 481

Text #12

Max Range: 3.3593. Min Range: -3.3593

Max Act: 3.1536. Min Act: -0.1700

Data Index: 652614 (Open Web Text)

Max Activating Token Index: 576

Text #13

Max Range: 3.3593. Min Range: -3.3593

Max Act: 3.1756. Min Act: -0.1700

Data Index: 7791552 (Open Web Text)

Max Activating Token Index: 164

Text #14

Max Range: 3.3593. Min Range: -3.3593

Max Act: 3.1841. Min Act: -0.1700

Data Index: 4867243 (Open Web Text)

Max Activating Token Index: 237

Text #15

Max Range: 3.3593. Min Range: -3.3593

Max Act: 3.1286. Min Act: -0.1700

Data Index: 2766569 (Open Web Text)

Max Activating Token Index: 512

Text #16

Max Range: 3.3593. Min Range: -3.3593

Max Act: 3.1307. Min Act: -0.1700

Data Index: 5744507 (Open Web Text)

Max Activating Token Index: 467

Text #17

Max Range: 3.3593. Min Range: -3.3593

Max Act: 3.1301. Min Act: -0.1700

Data Index: 864549 (Open Web Text)

Max Activating Token Index: 865

Text #18

Max Range: 3.3593. Min Range: -3.3593

Max Act: 3.1469. Min Act: -0.1700

Data Index: 8395097 (Open Web Text)

Max Activating Token Index: 482

Text #19

Max Range: 3.3593. Min Range: -3.3593

Max Act: 3.1242. Min Act: -0.1700

Data Index: 4419397 (Open Web Text)

Max Activating Token Index: 381