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

Dataset: Open Web Text

Neuron 2030 in Layer 1

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: 1.6301. Min Range: -1.6301

Max Act: 1.6233. Min Act: -0.1700

Data Index: 4456023 (Open Web Text)

Max Activating Token Index: 67

Text #1

Max Range: 1.6301. Min Range: -1.6301

Max Act: 1.6301. Min Act: -0.1700

Data Index: 4918104 (Open Web Text)

Max Activating Token Index: 493

Text #2

Max Range: 1.6301. Min Range: -1.6301

Max Act: 1.6134. Min Act: -0.1700

Data Index: 1649430 (Open Web Text)

Max Activating Token Index: 727

Text #3

Max Range: 1.6301. Min Range: -1.6301

Max Act: 1.6192. Min Act: -0.1700

Data Index: 3289675 (Open Web Text)

Max Activating Token Index: 944

Text #4

Max Range: 1.6301. Min Range: -1.6301

Max Act: 1.6063. Min Act: -0.1700

Data Index: 840959 (Open Web Text)

Max Activating Token Index: 531

Text #5

Max Range: 1.6301. Min Range: -1.6301

Max Act: 1.5975. Min Act: -0.1700

Data Index: 2459505 (Open Web Text)

Max Activating Token Index: 553

Text #6

Max Range: 1.6301. Min Range: -1.6301

Max Act: 1.5917. Min Act: -0.1700

Data Index: 2088480 (Open Web Text)

Max Activating Token Index: 543

Text #7

Max Range: 1.6301. Min Range: -1.6301

Max Act: 1.5938. Min Act: -0.1700

Data Index: 6209615 (Open Web Text)

Max Activating Token Index: 133

Text #8

Max Range: 1.6301. Min Range: -1.6301

Max Act: 1.5847. Min Act: -0.1700

Data Index: 2082157 (Open Web Text)

Max Activating Token Index: 959

Text #9

Max Range: 1.6301. Min Range: -1.6301

Max Act: 1.5858. Min Act: -0.1700

Data Index: 1238839 (Open Web Text)

Max Activating Token Index: 979

Text #10

Max Range: 1.6301. Min Range: -1.6301

Max Act: 1.5798. Min Act: -0.1700

Data Index: 1438336 (Open Web Text)

Max Activating Token Index: 206

Text #11

Max Range: 1.6301. Min Range: -1.6301

Max Act: 1.5760. Min Act: -0.1700

Data Index: 4726547 (Open Web Text)

Max Activating Token Index: 611

Text #12

Max Range: 1.6301. Min Range: -1.6301

Max Act: 1.5640. Min Act: -0.1700

Data Index: 5667400 (Open Web Text)

Max Activating Token Index: 185

Text #13

Max Range: 1.6301. Min Range: -1.6301

Max Act: 1.5795. Min Act: -0.1700

Data Index: 210074 (Open Web Text)

Max Activating Token Index: 853

Text #14

Max Range: 1.6301. Min Range: -1.6301

Max Act: 1.5667. Min Act: -0.1700

Data Index: 2541830 (Open Web Text)

Max Activating Token Index: 16

Text #15

Max Range: 1.6301. Min Range: -1.6301

Max Act: 1.5749. Min Act: -0.1700

Data Index: 786068 (Open Web Text)

Max Activating Token Index: 978

Text #16

Max Range: 1.6301. Min Range: -1.6301

Max Act: 1.5704. Min Act: -0.1700

Data Index: 3344387 (Open Web Text)

Max Activating Token Index: 198

Text #17

Max Range: 1.6301. Min Range: -1.6301

Max Act: 1.5743. Min Act: -0.1700

Data Index: 4126914 (Open Web Text)

Max Activating Token Index: 991

Text #18

Max Range: 1.6301. Min Range: -1.6301

Max Act: 1.5556. Min Act: -0.1700

Data Index: 4840740 (Open Web Text)

Max Activating Token Index: 772

Text #19

Max Range: 1.6301. Min Range: -1.6301

Max Act: 1.5642. Min Act: -0.1700

Data Index: 5453075 (Open Web Text)

Max Activating Token Index: 714