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

Dataset: Open Web Text

Neuron 504 in Layer 3

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: 5.5685. Min Range: -5.5685

Max Act: 5.5685. Min Act: -0.1700

Data Index: 6888261 (Open Web Text)

Max Activating Token Index: 526

Text #1

Max Range: 5.5685. Min Range: -5.5685

Max Act: 5.4790. Min Act: -0.1700

Data Index: 5143778 (Open Web Text)

Max Activating Token Index: 643

Text #2

Max Range: 5.5685. Min Range: -5.5685

Max Act: 5.3976. Min Act: -0.1700

Data Index: 2064579 (Open Web Text)

Max Activating Token Index: 175

Text #3

Max Range: 5.5685. Min Range: -5.5685

Max Act: 5.3454. Min Act: -0.1700

Data Index: 7397265 (Open Web Text)

Max Activating Token Index: 995

Text #4

Max Range: 5.5685. Min Range: -5.5685

Max Act: 5.3512. Min Act: -0.1700

Data Index: 1891319 (Open Web Text)

Max Activating Token Index: 771

Text #5

Max Range: 5.5685. Min Range: -5.5685

Max Act: 5.3197. Min Act: -0.1700

Data Index: 6837387 (Open Web Text)

Max Activating Token Index: 20

Text #6

Max Range: 5.5685. Min Range: -5.5685

Max Act: 5.3007. Min Act: -0.1700

Data Index: 3501382 (Open Web Text)

Max Activating Token Index: 343

Text #7

Max Range: 5.5685. Min Range: -5.5685

Max Act: 5.3271. Min Act: -0.1700

Data Index: 8509098 (Open Web Text)

Max Activating Token Index: 754

Text #8

Max Range: 5.5685. Min Range: -5.5685

Max Act: 5.2349. Min Act: -0.1700

Data Index: 5063471 (Open Web Text)

Max Activating Token Index: 725

Text #9

Max Range: 5.5685. Min Range: -5.5685

Max Act: 5.2877. Min Act: -0.1700

Data Index: 5318739 (Open Web Text)

Max Activating Token Index: 966

Text #10

Max Range: 5.5685. Min Range: -5.5685

Max Act: 5.2424. Min Act: -0.1700

Data Index: 26865 (Open Web Text)

Max Activating Token Index: 428

Text #11

Max Range: 5.5685. Min Range: -5.5685

Max Act: 5.2553. Min Act: -0.1700

Data Index: 2998335 (Open Web Text)

Max Activating Token Index: 981

Text #12

Max Range: 5.5685. Min Range: -5.5685

Max Act: 5.2255. Min Act: -0.1700

Data Index: 7409696 (Open Web Text)

Max Activating Token Index: 137

Text #13

Max Range: 5.5685. Min Range: -5.5685

Max Act: 5.2139. Min Act: -0.1700

Data Index: 4292604 (Open Web Text)

Max Activating Token Index: 833

Text #14

Max Range: 5.5685. Min Range: -5.5685

Max Act: 5.2286. Min Act: -0.1700

Data Index: 803344 (Open Web Text)

Max Activating Token Index: 560

Text #15

Max Range: 5.5685. Min Range: -5.5685

Max Act: 5.1968. Min Act: -0.1700

Data Index: 7277914 (Open Web Text)

Max Activating Token Index: 981

Text #16

Max Range: 5.5685. Min Range: -5.5685

Max Act: 5.2079. Min Act: -0.1700

Data Index: 3336928 (Open Web Text)

Max Activating Token Index: 976

Text #17

Max Range: 5.5685. Min Range: -5.5685

Max Act: 5.2154. Min Act: -0.1700

Data Index: 7371294 (Open Web Text)

Max Activating Token Index: 223

Text #18

Max Range: 5.5685. Min Range: -5.5685

Max Act: 5.2158. Min Act: -0.1700

Data Index: 7371289 (Open Web Text)

Max Activating Token Index: 708

Text #19

Max Range: 5.5685. Min Range: -5.5685

Max Act: 5.1773. Min Act: -0.1700

Data Index: 6420960 (Open Web Text)

Max Activating Token Index: 733