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

Dataset: Open Web Text

Neuron 492 in Layer 6

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: 4.6979. Min Range: -4.6979

Max Act: 4.6979. Min Act: -0.1700

Data Index: 5211555 (Open Web Text)

Max Activating Token Index: 24

Text #1

Max Range: 4.6979. Min Range: -4.6979

Max Act: 4.6398. Min Act: -0.1700

Data Index: 4861266 (Open Web Text)

Max Activating Token Index: 856

Text #2

Max Range: 4.6979. Min Range: -4.6979

Max Act: 4.5642. Min Act: -0.1700

Data Index: 7137540 (Open Web Text)

Max Activating Token Index: 237

Text #3

Max Range: 4.6979. Min Range: -4.6979

Max Act: 4.5589. Min Act: -0.1700

Data Index: 3724081 (Open Web Text)

Max Activating Token Index: 87

Text #4

Max Range: 4.6979. Min Range: -4.6979

Max Act: 4.5251. Min Act: -0.1700

Data Index: 8697563 (Open Web Text)

Max Activating Token Index: 150

Text #5

Max Range: 4.6979. Min Range: -4.6979

Max Act: 4.5605. Min Act: -0.1700

Data Index: 2622510 (Open Web Text)

Max Activating Token Index: 708

Text #6

Max Range: 4.6979. Min Range: -4.6979

Max Act: 4.4556. Min Act: -0.1700

Data Index: 1688687 (Open Web Text)

Max Activating Token Index: 218

Text #7

Max Range: 4.6979. Min Range: -4.6979

Max Act: 4.4191. Min Act: -0.1700

Data Index: 7830114 (Open Web Text)

Max Activating Token Index: 64

Text #8

Max Range: 4.6979. Min Range: -4.6979

Max Act: 4.4088. Min Act: -0.1700

Data Index: 4921511 (Open Web Text)

Max Activating Token Index: 917

Text #9

Max Range: 4.6979. Min Range: -4.6979

Max Act: 4.4243. Min Act: -0.1700

Data Index: 4941586 (Open Web Text)

Max Activating Token Index: 272

Text #10

Max Range: 4.6979. Min Range: -4.6979

Max Act: 4.2679. Min Act: -0.1700

Data Index: 4971810 (Open Web Text)

Max Activating Token Index: 546

Text #11

Max Range: 4.6979. Min Range: -4.6979

Max Act: 4.3032. Min Act: -0.1700

Data Index: 2914634 (Open Web Text)

Max Activating Token Index: 167

Text #12

Max Range: 4.6979. Min Range: -4.6979

Max Act: 4.2581. Min Act: -0.1700

Data Index: 7151327 (Open Web Text)

Max Activating Token Index: 235

Text #13

Max Range: 4.6979. Min Range: -4.6979

Max Act: 4.2294. Min Act: -0.1700

Data Index: 1131423 (Open Web Text)

Max Activating Token Index: 720

Text #14

Max Range: 4.6979. Min Range: -4.6979

Max Act: 4.2429. Min Act: -0.1700

Data Index: 3440335 (Open Web Text)

Max Activating Token Index: 360

Text #15

Max Range: 4.6979. Min Range: -4.6979

Max Act: 4.2297. Min Act: -0.1700

Data Index: 1354218 (Open Web Text)

Max Activating Token Index: 336

Text #16

Max Range: 4.6979. Min Range: -4.6979

Max Act: 4.1657. Min Act: -0.1700

Data Index: 4787771 (Open Web Text)

Max Activating Token Index: 802

Text #17

Max Range: 4.6979. Min Range: -4.6979

Max Act: 4.1779. Min Act: -0.1700

Data Index: 4373517 (Open Web Text)

Max Activating Token Index: 564

Text #18

Max Range: 4.6979. Min Range: -4.6979

Max Act: 4.1658. Min Act: -0.1700

Data Index: 4004784 (Open Web Text)

Max Activating Token Index: 231

Text #19

Max Range: 4.6979. Min Range: -4.6979

Max Act: 4.0873. Min Act: -0.1700

Data Index: 8390380 (Open Web Text)

Max Activating Token Index: 115