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

Dataset: Open Web Text

Neuron 336 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: 5.6223. Min Range: -5.6223

Max Act: 5.6223. Min Act: -0.1700

Data Index: 1606627 (Open Web Text)

Max Activating Token Index: 171

Text #1

Max Range: 5.6223. Min Range: -5.6223

Max Act: 5.6168. Min Act: -0.1700

Data Index: 6153625 (Open Web Text)

Max Activating Token Index: 509

Text #2

Max Range: 5.6223. Min Range: -5.6223

Max Act: 5.4848. Min Act: -0.1700

Data Index: 3171875 (Open Web Text)

Max Activating Token Index: 688

Text #3

Max Range: 5.6223. Min Range: -5.6223

Max Act: 5.3841. Min Act: -0.1700

Data Index: 4036520 (Open Web Text)

Max Activating Token Index: 318

Text #4

Max Range: 5.6223. Min Range: -5.6223

Max Act: 5.4199. Min Act: -0.1700

Data Index: 6443377 (Open Web Text)

Max Activating Token Index: 605

Text #5

Max Range: 5.6223. Min Range: -5.6223

Max Act: 5.4128. Min Act: -0.1700

Data Index: 2831647 (Open Web Text)

Max Activating Token Index: 597

Text #6

Max Range: 5.6223. Min Range: -5.6223

Max Act: 5.3624. Min Act: -0.1700

Data Index: 3482044 (Open Web Text)

Max Activating Token Index: 675

Text #7

Max Range: 5.6223. Min Range: -5.6223

Max Act: 5.3461. Min Act: -0.1700

Data Index: 5390811 (Open Web Text)

Max Activating Token Index: 302

Text #8

Max Range: 5.6223. Min Range: -5.6223

Max Act: 5.3161. Min Act: -0.1700

Data Index: 994716 (Open Web Text)

Max Activating Token Index: 453

Text #9

Max Range: 5.6223. Min Range: -5.6223

Max Act: 5.3216. Min Act: -0.1700

Data Index: 1235323 (Open Web Text)

Max Activating Token Index: 482

Text #10

Max Range: 5.6223. Min Range: -5.6223

Max Act: 5.2648. Min Act: -0.1700

Data Index: 3700791 (Open Web Text)

Max Activating Token Index: 959

Text #11

Max Range: 5.6223. Min Range: -5.6223

Max Act: 5.2699. Min Act: -0.1700

Data Index: 5594886 (Open Web Text)

Max Activating Token Index: 482

Text #12

Max Range: 5.6223. Min Range: -5.6223

Max Act: 5.2245. Min Act: -0.1700

Data Index: 6271238 (Open Web Text)

Max Activating Token Index: 836

Text #13

Max Range: 5.6223. Min Range: -5.6223

Max Act: 5.2235. Min Act: -0.1700

Data Index: 6412056 (Open Web Text)

Max Activating Token Index: 818

Text #14

Max Range: 5.6223. Min Range: -5.6223

Max Act: 5.1816. Min Act: -0.1700

Data Index: 375112 (Open Web Text)

Max Activating Token Index: 328

Text #15

Max Range: 5.6223. Min Range: -5.6223

Max Act: 5.2032. Min Act: -0.1700

Data Index: 4015325 (Open Web Text)

Max Activating Token Index: 201

Text #16

Max Range: 5.6223. Min Range: -5.6223

Max Act: 5.1715. Min Act: -0.1700

Data Index: 5774240 (Open Web Text)

Max Activating Token Index: 254

Text #17

Max Range: 5.6223. Min Range: -5.6223

Max Act: 5.1787. Min Act: -0.1700

Data Index: 191460 (Open Web Text)

Max Activating Token Index: 442

Text #18

Max Range: 5.6223. Min Range: -5.6223

Max Act: 5.1507. Min Act: -0.1700

Data Index: 636355 (Open Web Text)

Max Activating Token Index: 113

Text #19

Max Range: 5.6223. Min Range: -5.6223

Max Act: 5.1515. Min Act: -0.1700

Data Index: 3159238 (Open Web Text)

Max Activating Token Index: 934