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

Dataset: Open Web Text

Neuron 2360 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: 6.9306. Min Range: -6.9306

Max Act: 6.9306. Min Act: -0.1700

Data Index: 156306 (Open Web Text)

Max Activating Token Index: 444

Text #1

Max Range: 6.9306. Min Range: -6.9306

Max Act: 6.7081. Min Act: -0.1700

Data Index: 6374445 (Open Web Text)

Max Activating Token Index: 44

Text #2

Max Range: 6.9306. Min Range: -6.9306

Max Act: 6.7297. Min Act: -0.1700

Data Index: 2025842 (Open Web Text)

Max Activating Token Index: 103

Text #3

Max Range: 6.9306. Min Range: -6.9306

Max Act: 6.6519. Min Act: -0.1700

Data Index: 3624316 (Open Web Text)

Max Activating Token Index: 707

Text #4

Max Range: 6.9306. Min Range: -6.9306

Max Act: 6.6702. Min Act: -0.1700

Data Index: 4016544 (Open Web Text)

Max Activating Token Index: 529

Text #5

Max Range: 6.9306. Min Range: -6.9306

Max Act: 6.5626. Min Act: -0.1700

Data Index: 2218586 (Open Web Text)

Max Activating Token Index: 367

Text #6

Max Range: 6.9306. Min Range: -6.9306

Max Act: 6.5595. Min Act: -0.1700

Data Index: 1547983 (Open Web Text)

Max Activating Token Index: 276

Text #7

Max Range: 6.9306. Min Range: -6.9306

Max Act: 6.4505. Min Act: -0.1700

Data Index: 2554912 (Open Web Text)

Max Activating Token Index: 457

Text #8

Max Range: 6.9306. Min Range: -6.9306

Max Act: 6.5075. Min Act: -0.1700

Data Index: 6013834 (Open Web Text)

Max Activating Token Index: 289

Text #9

Max Range: 6.9306. Min Range: -6.9306

Max Act: 6.4226. Min Act: -0.1700

Data Index: 1520837 (Open Web Text)

Max Activating Token Index: 665

Text #10

Max Range: 6.9306. Min Range: -6.9306

Max Act: 6.3722. Min Act: -0.1700

Data Index: 583270 (Open Web Text)

Max Activating Token Index: 953

Text #11

Max Range: 6.9306. Min Range: -6.9306

Max Act: 6.3843. Min Act: -0.1700

Data Index: 8275869 (Open Web Text)

Max Activating Token Index: 185

Text #12

Max Range: 6.9306. Min Range: -6.9306

Max Act: 6.3410. Min Act: -0.1700

Data Index: 4179172 (Open Web Text)

Max Activating Token Index: 695

Text #13

Max Range: 6.9306. Min Range: -6.9306

Max Act: 6.2274. Min Act: -0.1700

Data Index: 5674815 (Open Web Text)

Max Activating Token Index: 178

Text #14

Max Range: 6.9306. Min Range: -6.9306

Max Act: 6.1688. Min Act: -0.1700

Data Index: 8508771 (Open Web Text)

Max Activating Token Index: 628

Text #15

Max Range: 6.9306. Min Range: -6.9306

Max Act: 6.2297. Min Act: -0.1700

Data Index: 7079166 (Open Web Text)

Max Activating Token Index: 267

Text #16

Max Range: 6.9306. Min Range: -6.9306

Max Act: 6.2771. Min Act: -0.1700

Data Index: 4309808 (Open Web Text)

Max Activating Token Index: 491

Text #17

Max Range: 6.9306. Min Range: -6.9306

Max Act: 6.1672. Min Act: -0.1700

Data Index: 4285891 (Open Web Text)

Max Activating Token Index: 967

Text #18

Max Range: 6.9306. Min Range: -6.9306

Max Act: 6.2047. Min Act: -0.1700

Data Index: 1968040 (Open Web Text)

Max Activating Token Index: 177

Text #19

Max Range: 6.9306. Min Range: -6.9306

Max Act: 6.2012. Min Act: -0.1700

Data Index: 5888099 (Open Web Text)

Max Activating Token Index: 995