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

Dataset: Open Web Text

Neuron 300 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: 3.2536. Min Range: -3.2536

Max Act: 3.2536. Min Act: -0.1700

Data Index: 3047711 (Open Web Text)

Max Activating Token Index: 202

Text #1

Max Range: 3.2536. Min Range: -3.2536

Max Act: 3.2228. Min Act: -0.1700

Data Index: 4794965 (Open Web Text)

Max Activating Token Index: 342

Text #2

Max Range: 3.2536. Min Range: -3.2536

Max Act: 3.1482. Min Act: -0.1700

Data Index: 7088863 (Open Web Text)

Max Activating Token Index: 152

Text #3

Max Range: 3.2536. Min Range: -3.2536

Max Act: 3.0938. Min Act: -0.1700

Data Index: 663499 (Open Web Text)

Max Activating Token Index: 388

Text #4

Max Range: 3.2536. Min Range: -3.2536

Max Act: 3.1163. Min Act: -0.1700

Data Index: 3039866 (Open Web Text)

Max Activating Token Index: 744

Text #5

Max Range: 3.2536. Min Range: -3.2536

Max Act: 3.0957. Min Act: -0.1700

Data Index: 6571097 (Open Web Text)

Max Activating Token Index: 598

Text #6

Max Range: 3.2536. Min Range: -3.2536

Max Act: 3.0916. Min Act: -0.1700

Data Index: 1931663 (Open Web Text)

Max Activating Token Index: 71

Text #7

Max Range: 3.2536. Min Range: -3.2536

Max Act: 3.0807. Min Act: -0.1700

Data Index: 5744322 (Open Web Text)

Max Activating Token Index: 185

Text #8

Max Range: 3.2536. Min Range: -3.2536

Max Act: 3.0473. Min Act: -0.1700

Data Index: 7039833 (Open Web Text)

Max Activating Token Index: 201

Text #9

Max Range: 3.2536. Min Range: -3.2536

Max Act: 3.0431. Min Act: -0.1700

Data Index: 4876286 (Open Web Text)

Max Activating Token Index: 562

Text #10

Max Range: 3.2536. Min Range: -3.2536

Max Act: 3.0263. Min Act: -0.1700

Data Index: 8275361 (Open Web Text)

Max Activating Token Index: 332

Text #11

Max Range: 3.2536. Min Range: -3.2536

Max Act: 3.0143. Min Act: -0.1700

Data Index: 5805859 (Open Web Text)

Max Activating Token Index: 675

Text #12

Max Range: 3.2536. Min Range: -3.2536

Max Act: 3.0200. Min Act: -0.1700

Data Index: 6282368 (Open Web Text)

Max Activating Token Index: 591

Text #13

Max Range: 3.2536. Min Range: -3.2536

Max Act: 3.0020. Min Act: -0.1700

Data Index: 7625834 (Open Web Text)

Max Activating Token Index: 299

Text #14

Max Range: 3.2536. Min Range: -3.2536

Max Act: 3.0241. Min Act: -0.1700

Data Index: 5134614 (Open Web Text)

Max Activating Token Index: 259

Text #15

Max Range: 3.2536. Min Range: -3.2536

Max Act: 2.9983. Min Act: -0.1700

Data Index: 1505052 (Open Web Text)

Max Activating Token Index: 76

Text #16

Max Range: 3.2536. Min Range: -3.2536

Max Act: 3.0066. Min Act: -0.1700

Data Index: 792315 (Open Web Text)

Max Activating Token Index: 184

Text #17

Max Range: 3.2536. Min Range: -3.2536

Max Act: 2.9954. Min Act: -0.1700

Data Index: 2519750 (Open Web Text)

Max Activating Token Index: 660

Text #18

Max Range: 3.2536. Min Range: -3.2536

Max Act: 2.9943. Min Act: -0.1700

Data Index: 4522288 (Open Web Text)

Max Activating Token Index: 87

Text #19

Max Range: 3.2536. Min Range: -3.2536

Max Act: 3.0026. Min Act: -0.1700

Data Index: 6386879 (Open Web Text)

Max Activating Token Index: 977