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

Dataset: Open Web Text

Neuron 1528 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: 3.0171. Min Range: -3.0171

Max Act: 3.0171. Min Act: -0.1700

Data Index: 7724571 (Open Web Text)

Max Activating Token Index: 345

Text #1

Max Range: 3.0171. Min Range: -3.0171

Max Act: 2.9989. Min Act: -0.1700

Data Index: 3474973 (Open Web Text)

Max Activating Token Index: 183

Text #2

Max Range: 3.0171. Min Range: -3.0171

Max Act: 3.0085. Min Act: -0.1700

Data Index: 1292325 (Open Web Text)

Max Activating Token Index: 891

Text #3

Max Range: 3.0171. Min Range: -3.0171

Max Act: 2.9650. Min Act: -0.1700

Data Index: 1884342 (Open Web Text)

Max Activating Token Index: 748

Text #4

Max Range: 3.0171. Min Range: -3.0171

Max Act: 2.9591. Min Act: -0.1700

Data Index: 7792614 (Open Web Text)

Max Activating Token Index: 639

Text #5

Max Range: 3.0171. Min Range: -3.0171

Max Act: 2.9488. Min Act: -0.1700

Data Index: 3509207 (Open Web Text)

Max Activating Token Index: 613

Text #6

Max Range: 3.0171. Min Range: -3.0171

Max Act: 2.9732. Min Act: -0.1700

Data Index: 3725042 (Open Web Text)

Max Activating Token Index: 489

Text #7

Max Range: 3.0171. Min Range: -3.0171

Max Act: 2.9367. Min Act: -0.1700

Data Index: 3500857 (Open Web Text)

Max Activating Token Index: 748

Text #8

Max Range: 3.0171. Min Range: -3.0171

Max Act: 2.9396. Min Act: -0.1700

Data Index: 4903519 (Open Web Text)

Max Activating Token Index: 614

Text #9

Max Range: 3.0171. Min Range: -3.0171

Max Act: 2.9161. Min Act: -0.1700

Data Index: 4817280 (Open Web Text)

Max Activating Token Index: 981

Text #10

Max Range: 3.0171. Min Range: -3.0171

Max Act: 2.9225. Min Act: -0.1700

Data Index: 7101607 (Open Web Text)

Max Activating Token Index: 546

Text #11

Max Range: 3.0171. Min Range: -3.0171

Max Act: 2.9170. Min Act: -0.1700

Data Index: 7110563 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 3.0171. Min Range: -3.0171

Max Act: 2.9036. Min Act: -0.1700

Data Index: 380357 (Open Web Text)

Max Activating Token Index: 1011

Text #13

Max Range: 3.0171. Min Range: -3.0171

Max Act: 2.9036. Min Act: -0.1700

Data Index: 4303463 (Open Web Text)

Max Activating Token Index: 491

Text #14

Max Range: 3.0171. Min Range: -3.0171

Max Act: 2.9105. Min Act: -0.1700

Data Index: 307792 (Open Web Text)

Max Activating Token Index: 452

Text #15

Max Range: 3.0171. Min Range: -3.0171

Max Act: 2.9323. Min Act: -0.1700

Data Index: 4377067 (Open Web Text)

Max Activating Token Index: 489

Text #16

Max Range: 3.0171. Min Range: -3.0171

Max Act: 2.9093. Min Act: -0.1700

Data Index: 6161103 (Open Web Text)

Max Activating Token Index: 191

Text #17

Max Range: 3.0171. Min Range: -3.0171

Max Act: 2.9143. Min Act: -0.1700

Data Index: 6782266 (Open Web Text)

Max Activating Token Index: 481

Text #18

Max Range: 3.0171. Min Range: -3.0171

Max Act: 2.9129. Min Act: -0.1700

Data Index: 2453847 (Open Web Text)

Max Activating Token Index: 71

Text #19

Max Range: 3.0171. Min Range: -3.0171

Max Act: 2.9295. Min Act: -0.1700

Data Index: 4893984 (Open Web Text)

Max Activating Token Index: 488