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

Dataset: Open Web Text

Neuron 2968 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: 3.4333. Min Range: -3.4333

Max Act: 3.4333. Min Act: -0.1700

Data Index: 6301749 (Open Web Text)

Max Activating Token Index: 243

Text #1

Max Range: 3.4333. Min Range: -3.4333

Max Act: 3.3997. Min Act: -0.1700

Data Index: 4809664 (Open Web Text)

Max Activating Token Index: 694

Text #2

Max Range: 3.4333. Min Range: -3.4333

Max Act: 3.3790. Min Act: -0.1700

Data Index: 8534807 (Open Web Text)

Max Activating Token Index: 823

Text #3

Max Range: 3.4333. Min Range: -3.4333

Max Act: 3.3901. Min Act: -0.1700

Data Index: 4475701 (Open Web Text)

Max Activating Token Index: 34

Text #4

Max Range: 3.4333. Min Range: -3.4333

Max Act: 3.3350. Min Act: -0.1700

Data Index: 48846 (Open Web Text)

Max Activating Token Index: 762

Text #5

Max Range: 3.4333. Min Range: -3.4333

Max Act: 3.3553. Min Act: -0.1700

Data Index: 8618430 (Open Web Text)

Max Activating Token Index: 641

Text #6

Max Range: 3.4333. Min Range: -3.4333

Max Act: 3.3311. Min Act: -0.1700

Data Index: 7024568 (Open Web Text)

Max Activating Token Index: 144

Text #7

Max Range: 3.4333. Min Range: -3.4333

Max Act: 3.3195. Min Act: -0.1700

Data Index: 5295473 (Open Web Text)

Max Activating Token Index: 275

Text #8

Max Range: 3.4333. Min Range: -3.4333

Max Act: 3.3166. Min Act: -0.1700

Data Index: 2939628 (Open Web Text)

Max Activating Token Index: 553

Text #9

Max Range: 3.4333. Min Range: -3.4333

Max Act: 3.2829. Min Act: -0.1700

Data Index: 5577001 (Open Web Text)

Max Activating Token Index: 552

Text #10

Max Range: 3.4333. Min Range: -3.4333

Max Act: 3.3029. Min Act: -0.1700

Data Index: 3105093 (Open Web Text)

Max Activating Token Index: 755

Text #11

Max Range: 3.4333. Min Range: -3.4333

Max Act: 3.2700. Min Act: -0.1700

Data Index: 4972038 (Open Web Text)

Max Activating Token Index: 719

Text #12

Max Range: 3.4333. Min Range: -3.4333

Max Act: 3.2673. Min Act: -0.1700

Data Index: 8275756 (Open Web Text)

Max Activating Token Index: 199

Text #13

Max Range: 3.4333. Min Range: -3.4333

Max Act: 3.2777. Min Act: -0.1700

Data Index: 4318777 (Open Web Text)

Max Activating Token Index: 270

Text #14

Max Range: 3.4333. Min Range: -3.4333

Max Act: 3.2547. Min Act: -0.1700

Data Index: 3500416 (Open Web Text)

Max Activating Token Index: 919

Text #15

Max Range: 3.4333. Min Range: -3.4333

Max Act: 3.2533. Min Act: -0.1700

Data Index: 6266174 (Open Web Text)

Max Activating Token Index: 49

Text #16

Max Range: 3.4333. Min Range: -3.4333

Max Act: 3.2458. Min Act: -0.1700

Data Index: 7872108 (Open Web Text)

Max Activating Token Index: 290

Text #17

Max Range: 3.4333. Min Range: -3.4333

Max Act: 3.2372. Min Act: -0.1700

Data Index: 2632904 (Open Web Text)

Max Activating Token Index: 142

Text #18

Max Range: 3.4333. Min Range: -3.4333

Max Act: 3.2279. Min Act: -0.1700

Data Index: 2352588 (Open Web Text)

Max Activating Token Index: 153

Text #19

Max Range: 3.4333. Min Range: -3.4333

Max Act: 3.2227. Min Act: -0.1700

Data Index: 4496831 (Open Web Text)

Max Activating Token Index: 1014