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

Dataset: Open Web Text

Neuron 1108 in Layer 2

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: 3.4503. Min Range: -3.4503

Max Act: 3.4503. Min Act: -0.1700

Data Index: 2071244 (Open Web Text)

Max Activating Token Index: 602

Text #1

Max Range: 3.4503. Min Range: -3.4503

Max Act: 3.3636. Min Act: -0.1700

Data Index: 912996 (Open Web Text)

Max Activating Token Index: 372

Text #2

Max Range: 3.4503. Min Range: -3.4503

Max Act: 3.2788. Min Act: -0.1700

Data Index: 2697059 (Open Web Text)

Max Activating Token Index: 180

Text #3

Max Range: 3.4503. Min Range: -3.4503

Max Act: 3.3250. Min Act: -0.1700

Data Index: 6435724 (Open Web Text)

Max Activating Token Index: 548

Text #4

Max Range: 3.4503. Min Range: -3.4503

Max Act: 3.2773. Min Act: -0.1700

Data Index: 3259540 (Open Web Text)

Max Activating Token Index: 1005

Text #5

Max Range: 3.4503. Min Range: -3.4503

Max Act: 3.2641. Min Act: -0.1700

Data Index: 1558203 (Open Web Text)

Max Activating Token Index: 730

Text #6

Max Range: 3.4503. Min Range: -3.4503

Max Act: 3.2872. Min Act: -0.1700

Data Index: 7918064 (Open Web Text)

Max Activating Token Index: 581

Text #7

Max Range: 3.4503. Min Range: -3.4503

Max Act: 3.2249. Min Act: -0.1700

Data Index: 693962 (Open Web Text)

Max Activating Token Index: 456

Text #8

Max Range: 3.4503. Min Range: -3.4503

Max Act: 3.2922. Min Act: -0.1700

Data Index: 1102002 (Open Web Text)

Max Activating Token Index: 445

Text #9

Max Range: 3.4503. Min Range: -3.4503

Max Act: 3.2185. Min Act: -0.1700

Data Index: 4424104 (Open Web Text)

Max Activating Token Index: 335

Text #10

Max Range: 3.4503. Min Range: -3.4503

Max Act: 3.2246. Min Act: -0.1700

Data Index: 2798408 (Open Web Text)

Max Activating Token Index: 786

Text #11

Max Range: 3.4503. Min Range: -3.4503

Max Act: 3.2115. Min Act: -0.1700

Data Index: 6989283 (Open Web Text)

Max Activating Token Index: 117

Text #12

Max Range: 3.4503. Min Range: -3.4503

Max Act: 3.2593. Min Act: -0.1700

Data Index: 6345470 (Open Web Text)

Max Activating Token Index: 413

Text #13

Max Range: 3.4503. Min Range: -3.4503

Max Act: 3.2213. Min Act: -0.1700

Data Index: 8791819 (Open Web Text)

Max Activating Token Index: 102

Text #14

Max Range: 3.4503. Min Range: -3.4503

Max Act: 3.1903. Min Act: -0.1700

Data Index: 1620078 (Open Web Text)

Max Activating Token Index: 368

Text #15

Max Range: 3.4503. Min Range: -3.4503

Max Act: 3.2214. Min Act: -0.1700

Data Index: 2563708 (Open Web Text)

Max Activating Token Index: 692

Text #16

Max Range: 3.4503. Min Range: -3.4503

Max Act: 3.1989. Min Act: -0.1700

Data Index: 7727684 (Open Web Text)

Max Activating Token Index: 413

Text #17

Max Range: 3.4503. Min Range: -3.4503

Max Act: 3.1744. Min Act: -0.1700

Data Index: 6125087 (Open Web Text)

Max Activating Token Index: 973

Text #18

Max Range: 3.4503. Min Range: -3.4503

Max Act: 3.2048. Min Act: -0.1700

Data Index: 2060537 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 3.4503. Min Range: -3.4503

Max Act: 3.2426. Min Act: -0.1700

Data Index: 36841 (Open Web Text)

Max Activating Token Index: 458