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

Dataset: Open Web Text

Neuron 2689 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: 3.3440. Min Range: -3.3440

Max Act: 3.3440. Min Act: -0.1700

Data Index: 4977250 (Open Web Text)

Max Activating Token Index: 445

Text #1

Max Range: 3.3440. Min Range: -3.3440

Max Act: 3.3399. Min Act: -0.1700

Data Index: 6580480 (Open Web Text)

Max Activating Token Index: 308

Text #2

Max Range: 3.3440. Min Range: -3.3440

Max Act: 3.3002. Min Act: -0.1700

Data Index: 2593051 (Open Web Text)

Max Activating Token Index: 225

Text #3

Max Range: 3.3440. Min Range: -3.3440

Max Act: 3.2720. Min Act: -0.1700

Data Index: 3391202 (Open Web Text)

Max Activating Token Index: 10

Text #4

Max Range: 3.3440. Min Range: -3.3440

Max Act: 3.2842. Min Act: -0.1700

Data Index: 2973076 (Open Web Text)

Max Activating Token Index: 662

Text #5

Max Range: 3.3440. Min Range: -3.3440

Max Act: 3.2632. Min Act: -0.1700

Data Index: 1926476 (Open Web Text)

Max Activating Token Index: 491

Text #6

Max Range: 3.3440. Min Range: -3.3440

Max Act: 3.2389. Min Act: -0.1700

Data Index: 1459998 (Open Web Text)

Max Activating Token Index: 832

Text #7

Max Range: 3.3440. Min Range: -3.3440

Max Act: 3.2341. Min Act: -0.1700

Data Index: 821125 (Open Web Text)

Max Activating Token Index: 309

Text #8

Max Range: 3.3440. Min Range: -3.3440

Max Act: 3.2120. Min Act: -0.1700

Data Index: 2858006 (Open Web Text)

Max Activating Token Index: 245

Text #9

Max Range: 3.3440. Min Range: -3.3440

Max Act: 3.1782. Min Act: -0.1700

Data Index: 7173086 (Open Web Text)

Max Activating Token Index: 274

Text #10

Max Range: 3.3440. Min Range: -3.3440

Max Act: 3.1840. Min Act: -0.1700

Data Index: 7173087 (Open Web Text)

Max Activating Token Index: 364

Text #11

Max Range: 3.3440. Min Range: -3.3440

Max Act: 3.1760. Min Act: -0.1700

Data Index: 5655878 (Open Web Text)

Max Activating Token Index: 529

Text #12

Max Range: 3.3440. Min Range: -3.3440

Max Act: 3.1350. Min Act: -0.1700

Data Index: 5783224 (Open Web Text)

Max Activating Token Index: 546

Text #13

Max Range: 3.3440. Min Range: -3.3440

Max Act: 3.1828. Min Act: -0.1700

Data Index: 6591524 (Open Web Text)

Max Activating Token Index: 457

Text #14

Max Range: 3.3440. Min Range: -3.3440

Max Act: 3.1720. Min Act: -0.1700

Data Index: 1256854 (Open Web Text)

Max Activating Token Index: 302

Text #15

Max Range: 3.3440. Min Range: -3.3440

Max Act: 3.1179. Min Act: -0.1700

Data Index: 3922016 (Open Web Text)

Max Activating Token Index: 730

Text #16

Max Range: 3.3440. Min Range: -3.3440

Max Act: 3.1530. Min Act: -0.1700

Data Index: 5599880 (Open Web Text)

Max Activating Token Index: 190

Text #17

Max Range: 3.3440. Min Range: -3.3440

Max Act: 3.1463. Min Act: -0.1700

Data Index: 4395877 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 3.3440. Min Range: -3.3440

Max Act: 3.1744. Min Act: -0.1700

Data Index: 1182420 (Open Web Text)

Max Activating Token Index: 426

Text #19

Max Range: 3.3440. Min Range: -3.3440

Max Act: 3.1373. Min Act: -0.1700

Data Index: 1094935 (Open Web Text)

Max Activating Token Index: 49