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

Dataset: Open Web Text

Neuron 1127 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: 3.5171. Min Range: -3.5171

Max Act: 3.5171. Min Act: -0.1700

Data Index: 4081897 (Open Web Text)

Max Activating Token Index: 54

Text #1

Max Range: 3.5171. Min Range: -3.5171

Max Act: 3.4932. Min Act: -0.1700

Data Index: 1086854 (Open Web Text)

Max Activating Token Index: 893

Text #2

Max Range: 3.5171. Min Range: -3.5171

Max Act: 3.4925. Min Act: -0.1700

Data Index: 3759069 (Open Web Text)

Max Activating Token Index: 165

Text #3

Max Range: 3.5171. Min Range: -3.5171

Max Act: 3.4750. Min Act: -0.1700

Data Index: 2051962 (Open Web Text)

Max Activating Token Index: 71

Text #4

Max Range: 3.5171. Min Range: -3.5171

Max Act: 3.4741. Min Act: -0.1700

Data Index: 5656640 (Open Web Text)

Max Activating Token Index: 863

Text #5

Max Range: 3.5171. Min Range: -3.5171

Max Act: 3.4786. Min Act: -0.1700

Data Index: 4095553 (Open Web Text)

Max Activating Token Index: 588

Text #6

Max Range: 3.5171. Min Range: -3.5171

Max Act: 3.4645. Min Act: -0.1700

Data Index: 4369064 (Open Web Text)

Max Activating Token Index: 260

Text #7

Max Range: 3.5171. Min Range: -3.5171

Max Act: 3.4497. Min Act: -0.1700

Data Index: 3972271 (Open Web Text)

Max Activating Token Index: 299

Text #8

Max Range: 3.5171. Min Range: -3.5171

Max Act: 3.4331. Min Act: -0.1700

Data Index: 4087982 (Open Web Text)

Max Activating Token Index: 296

Text #9

Max Range: 3.5171. Min Range: -3.5171

Max Act: 3.4319. Min Act: -0.1700

Data Index: 433085 (Open Web Text)

Max Activating Token Index: 699

Text #10

Max Range: 3.5171. Min Range: -3.5171

Max Act: 3.4434. Min Act: -0.1700

Data Index: 807041 (Open Web Text)

Max Activating Token Index: 289

Text #11

Max Range: 3.5171. Min Range: -3.5171

Max Act: 3.4392. Min Act: -0.1700

Data Index: 6511291 (Open Web Text)

Max Activating Token Index: 40

Text #12

Max Range: 3.5171. Min Range: -3.5171

Max Act: 3.4274. Min Act: -0.1700

Data Index: 8308926 (Open Web Text)

Max Activating Token Index: 278

Text #13

Max Range: 3.5171. Min Range: -3.5171

Max Act: 3.4139. Min Act: -0.1700

Data Index: 1833482 (Open Web Text)

Max Activating Token Index: 261

Text #14

Max Range: 3.5171. Min Range: -3.5171

Max Act: 3.4333. Min Act: -0.1700

Data Index: 1957477 (Open Web Text)

Max Activating Token Index: 766

Text #15

Max Range: 3.5171. Min Range: -3.5171

Max Act: 3.4183. Min Act: -0.1700

Data Index: 7878421 (Open Web Text)

Max Activating Token Index: 841

Text #16

Max Range: 3.5171. Min Range: -3.5171

Max Act: 3.4214. Min Act: -0.1700

Data Index: 530709 (Open Web Text)

Max Activating Token Index: 536

Text #17

Max Range: 3.5171. Min Range: -3.5171

Max Act: 3.3947. Min Act: -0.1700

Data Index: 6976895 (Open Web Text)

Max Activating Token Index: 238

Text #18

Max Range: 3.5171. Min Range: -3.5171

Max Act: 3.3686. Min Act: -0.1700

Data Index: 2756607 (Open Web Text)

Max Activating Token Index: 380

Text #19

Max Range: 3.5171. Min Range: -3.5171

Max Act: 3.3981. Min Act: -0.1700

Data Index: 3753266 (Open Web Text)

Max Activating Token Index: 224