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

Dataset: Open Web Text

Neuron 195 in Layer 5

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: 5.3997. Min Range: -5.3997

Max Act: 5.3997. Min Act: -0.1700

Data Index: 1353441 (Open Web Text)

Max Activating Token Index: 250

Text #1

Max Range: 5.3997. Min Range: -5.3997

Max Act: 5.3497. Min Act: -0.1700

Data Index: 8821359 (Open Web Text)

Max Activating Token Index: 341

Text #2

Max Range: 5.3997. Min Range: -5.3997

Max Act: 5.3931. Min Act: -0.1700

Data Index: 5261467 (Open Web Text)

Max Activating Token Index: 594

Text #3

Max Range: 5.3997. Min Range: -5.3997

Max Act: 5.3720. Min Act: -0.1700

Data Index: 6299804 (Open Web Text)

Max Activating Token Index: 295

Text #4

Max Range: 5.3997. Min Range: -5.3997

Max Act: 5.2991. Min Act: -0.1700

Data Index: 2915595 (Open Web Text)

Max Activating Token Index: 719

Text #5

Max Range: 5.3997. Min Range: -5.3997

Max Act: 5.3206. Min Act: -0.1700

Data Index: 3530518 (Open Web Text)

Max Activating Token Index: 958

Text #6

Max Range: 5.3997. Min Range: -5.3997

Max Act: 5.3224. Min Act: -0.1700

Data Index: 1186817 (Open Web Text)

Max Activating Token Index: 81

Text #7

Max Range: 5.3997. Min Range: -5.3997

Max Act: 5.2744. Min Act: -0.1700

Data Index: 6760893 (Open Web Text)

Max Activating Token Index: 295

Text #8

Max Range: 5.3997. Min Range: -5.3997

Max Act: 5.2337. Min Act: -0.1700

Data Index: 8230844 (Open Web Text)

Max Activating Token Index: 833

Text #9

Max Range: 5.3997. Min Range: -5.3997

Max Act: 5.2410. Min Act: -0.1700

Data Index: 4444022 (Open Web Text)

Max Activating Token Index: 84

Text #10

Max Range: 5.3997. Min Range: -5.3997

Max Act: 5.2253. Min Act: -0.1700

Data Index: 7189643 (Open Web Text)

Max Activating Token Index: 495

Text #11

Max Range: 5.3997. Min Range: -5.3997

Max Act: 5.2233. Min Act: -0.1700

Data Index: 3327773 (Open Web Text)

Max Activating Token Index: 304

Text #12

Max Range: 5.3997. Min Range: -5.3997

Max Act: 5.1968. Min Act: -0.1700

Data Index: 5087783 (Open Web Text)

Max Activating Token Index: 419

Text #13

Max Range: 5.3997. Min Range: -5.3997

Max Act: 5.1900. Min Act: -0.1700

Data Index: 2130704 (Open Web Text)

Max Activating Token Index: 268

Text #14

Max Range: 5.3997. Min Range: -5.3997

Max Act: 5.1603. Min Act: -0.1700

Data Index: 4807267 (Open Web Text)

Max Activating Token Index: 685

Text #15

Max Range: 5.3997. Min Range: -5.3997

Max Act: 5.1689. Min Act: -0.1700

Data Index: 2550064 (Open Web Text)

Max Activating Token Index: 564

Text #16

Max Range: 5.3997. Min Range: -5.3997

Max Act: 5.1630. Min Act: -0.1700

Data Index: 2057708 (Open Web Text)

Max Activating Token Index: 406

Text #17

Max Range: 5.3997. Min Range: -5.3997

Max Act: 5.1859. Min Act: -0.1700

Data Index: 3263004 (Open Web Text)

Max Activating Token Index: 721

Text #18

Max Range: 5.3997. Min Range: -5.3997

Max Act: 5.1627. Min Act: -0.1700

Data Index: 2641403 (Open Web Text)

Max Activating Token Index: 139

Text #19

Max Range: 5.3997. Min Range: -5.3997

Max Act: 5.1766. Min Act: -0.1700

Data Index: 5560244 (Open Web Text)

Max Activating Token Index: 651