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

Dataset: Open Web Text

Neuron 2457 in Layer 3

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: 4.6301. Min Range: -4.6301

Max Act: 4.6153. Min Act: -0.1700

Data Index: 1333484 (Open Web Text)

Max Activating Token Index: 60

Text #1

Max Range: 4.6301. Min Range: -4.6301

Max Act: 4.6301. Min Act: -0.1700

Data Index: 1788685 (Open Web Text)

Max Activating Token Index: 806

Text #2

Max Range: 4.6301. Min Range: -4.6301

Max Act: 4.5835. Min Act: -0.1700

Data Index: 7300156 (Open Web Text)

Max Activating Token Index: 573

Text #3

Max Range: 4.6301. Min Range: -4.6301

Max Act: 4.5080. Min Act: -0.1700

Data Index: 4376155 (Open Web Text)

Max Activating Token Index: 957

Text #4

Max Range: 4.6301. Min Range: -4.6301

Max Act: 4.5015. Min Act: -0.1700

Data Index: 8022237 (Open Web Text)

Max Activating Token Index: 450

Text #5

Max Range: 4.6301. Min Range: -4.6301

Max Act: 4.5483. Min Act: -0.1700

Data Index: 5403227 (Open Web Text)

Max Activating Token Index: 745

Text #6

Max Range: 4.6301. Min Range: -4.6301

Max Act: 4.5031. Min Act: -0.1700

Data Index: 489536 (Open Web Text)

Max Activating Token Index: 864

Text #7

Max Range: 4.6301. Min Range: -4.6301

Max Act: 4.4730. Min Act: -0.1700

Data Index: 6061234 (Open Web Text)

Max Activating Token Index: 116

Text #8

Max Range: 4.6301. Min Range: -4.6301

Max Act: 4.4932. Min Act: -0.1700

Data Index: 7773362 (Open Web Text)

Max Activating Token Index: 89

Text #9

Max Range: 4.6301. Min Range: -4.6301

Max Act: 4.4745. Min Act: -0.1700

Data Index: 1566303 (Open Web Text)

Max Activating Token Index: 571

Text #10

Max Range: 4.6301. Min Range: -4.6301

Max Act: 4.4570. Min Act: -0.1700

Data Index: 4122930 (Open Web Text)

Max Activating Token Index: 415

Text #11

Max Range: 4.6301. Min Range: -4.6301

Max Act: 4.3942. Min Act: -0.1700

Data Index: 4274071 (Open Web Text)

Max Activating Token Index: 40

Text #12

Max Range: 4.6301. Min Range: -4.6301

Max Act: 4.4305. Min Act: -0.1700

Data Index: 1812219 (Open Web Text)

Max Activating Token Index: 51

Text #13

Max Range: 4.6301. Min Range: -4.6301

Max Act: 4.4419. Min Act: -0.1700

Data Index: 1306016 (Open Web Text)

Max Activating Token Index: 681

Text #14

Max Range: 4.6301. Min Range: -4.6301

Max Act: 4.4405. Min Act: -0.1700

Data Index: 7087700 (Open Web Text)

Max Activating Token Index: 341

Text #15

Max Range: 4.6301. Min Range: -4.6301

Max Act: 4.4242. Min Act: -0.1700

Data Index: 3084616 (Open Web Text)

Max Activating Token Index: 361

Text #16

Max Range: 4.6301. Min Range: -4.6301

Max Act: 4.3747. Min Act: -0.1700

Data Index: 5663468 (Open Web Text)

Max Activating Token Index: 174

Text #17

Max Range: 4.6301. Min Range: -4.6301

Max Act: 4.4188. Min Act: -0.1700

Data Index: 8401537 (Open Web Text)

Max Activating Token Index: 350

Text #18

Max Range: 4.6301. Min Range: -4.6301

Max Act: 4.4094. Min Act: -0.1700

Data Index: 8106658 (Open Web Text)

Max Activating Token Index: 297

Text #19

Max Range: 4.6301. Min Range: -4.6301

Max Act: 4.3940. Min Act: -0.1700

Data Index: 3193242 (Open Web Text)

Max Activating Token Index: 865