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

Dataset: Open Web Text

Neuron 193 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: 4.5265. Min Range: -4.5265

Max Act: 4.5265. Min Act: -0.1700

Data Index: 7656828 (Open Web Text)

Max Activating Token Index: 904

Text #1

Max Range: 4.5265. Min Range: -4.5265

Max Act: 4.5103. Min Act: -0.1700

Data Index: 8731728 (Open Web Text)

Max Activating Token Index: 625

Text #2

Max Range: 4.5265. Min Range: -4.5265

Max Act: 4.4953. Min Act: -0.1700

Data Index: 2328045 (Open Web Text)

Max Activating Token Index: 601

Text #3

Max Range: 4.5265. Min Range: -4.5265

Max Act: 4.4610. Min Act: -0.1700

Data Index: 8523878 (Open Web Text)

Max Activating Token Index: 374

Text #4

Max Range: 4.5265. Min Range: -4.5265

Max Act: 4.4657. Min Act: -0.1700

Data Index: 6704817 (Open Web Text)

Max Activating Token Index: 434

Text #5

Max Range: 4.5265. Min Range: -4.5265

Max Act: 4.4494. Min Act: -0.1700

Data Index: 5526637 (Open Web Text)

Max Activating Token Index: 142

Text #6

Max Range: 4.5265. Min Range: -4.5265

Max Act: 4.4272. Min Act: -0.1700

Data Index: 4270810 (Open Web Text)

Max Activating Token Index: 397

Text #7

Max Range: 4.5265. Min Range: -4.5265

Max Act: 4.4137. Min Act: -0.1700

Data Index: 5187965 (Open Web Text)

Max Activating Token Index: 455

Text #8

Max Range: 4.5265. Min Range: -4.5265

Max Act: 4.4065. Min Act: -0.1700

Data Index: 7759049 (Open Web Text)

Max Activating Token Index: 835

Text #9

Max Range: 4.5265. Min Range: -4.5265

Max Act: 4.4050. Min Act: -0.1700

Data Index: 8668171 (Open Web Text)

Max Activating Token Index: 652

Text #10

Max Range: 4.5265. Min Range: -4.5265

Max Act: 4.3715. Min Act: -0.1700

Data Index: 4572075 (Open Web Text)

Max Activating Token Index: 26

Text #11

Max Range: 4.5265. Min Range: -4.5265

Max Act: 4.3923. Min Act: -0.1700

Data Index: 421565 (Open Web Text)

Max Activating Token Index: 310

Text #12

Max Range: 4.5265. Min Range: -4.5265

Max Act: 4.3809. Min Act: -0.1700

Data Index: 7627807 (Open Web Text)

Max Activating Token Index: 208

Text #13

Max Range: 4.5265. Min Range: -4.5265

Max Act: 4.3631. Min Act: -0.1700

Data Index: 1626574 (Open Web Text)

Max Activating Token Index: 669

Text #14

Max Range: 4.5265. Min Range: -4.5265

Max Act: 4.3490. Min Act: -0.1700

Data Index: 3334141 (Open Web Text)

Max Activating Token Index: 1004

Text #15

Max Range: 4.5265. Min Range: -4.5265

Max Act: 4.3676. Min Act: -0.1700

Data Index: 662867 (Open Web Text)

Max Activating Token Index: 963

Text #16

Max Range: 4.5265. Min Range: -4.5265

Max Act: 4.3399. Min Act: -0.1700

Data Index: 7608730 (Open Web Text)

Max Activating Token Index: 350

Text #17

Max Range: 4.5265. Min Range: -4.5265

Max Act: 4.3044. Min Act: -0.1700

Data Index: 5088646 (Open Web Text)

Max Activating Token Index: 539

Text #18

Max Range: 4.5265. Min Range: -4.5265

Max Act: 4.3041. Min Act: -0.1700

Data Index: 6318668 (Open Web Text)

Max Activating Token Index: 860

Text #19

Max Range: 4.5265. Min Range: -4.5265

Max Act: 4.3391. Min Act: -0.1700

Data Index: 2400590 (Open Web Text)

Max Activating Token Index: 167