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

Dataset: Open Web Text

Neuron 2495 in Layer 4

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: 4.4726. Min Range: -4.4726

Max Act: 4.4726. Min Act: -0.1700

Data Index: 6645551 (Open Web Text)

Max Activating Token Index: 243

Text #1

Max Range: 4.4726. Min Range: -4.4726

Max Act: 4.4408. Min Act: -0.1700

Data Index: 4297289 (Open Web Text)

Max Activating Token Index: 1004

Text #2

Max Range: 4.4726. Min Range: -4.4726

Max Act: 4.3847. Min Act: -0.1700

Data Index: 2222928 (Open Web Text)

Max Activating Token Index: 677

Text #3

Max Range: 4.4726. Min Range: -4.4726

Max Act: 4.3635. Min Act: -0.1700

Data Index: 1411454 (Open Web Text)

Max Activating Token Index: 790

Text #4

Max Range: 4.4726. Min Range: -4.4726

Max Act: 4.3696. Min Act: -0.1700

Data Index: 4989276 (Open Web Text)

Max Activating Token Index: 306

Text #5

Max Range: 4.4726. Min Range: -4.4726

Max Act: 4.3896. Min Act: -0.1700

Data Index: 2276284 (Open Web Text)

Max Activating Token Index: 771

Text #6

Max Range: 4.4726. Min Range: -4.4726

Max Act: 4.3424. Min Act: -0.1700

Data Index: 5719958 (Open Web Text)

Max Activating Token Index: 313

Text #7

Max Range: 4.4726. Min Range: -4.4726

Max Act: 4.3080. Min Act: -0.1700

Data Index: 4995159 (Open Web Text)

Max Activating Token Index: 490

Text #8

Max Range: 4.4726. Min Range: -4.4726

Max Act: 4.3143. Min Act: -0.1700

Data Index: 5137888 (Open Web Text)

Max Activating Token Index: 471

Text #9

Max Range: 4.4726. Min Range: -4.4726

Max Act: 4.3060. Min Act: -0.1700

Data Index: 3608960 (Open Web Text)

Max Activating Token Index: 839

Text #10

Max Range: 4.4726. Min Range: -4.4726

Max Act: 4.2949. Min Act: -0.1700

Data Index: 7835456 (Open Web Text)

Max Activating Token Index: 123

Text #11

Max Range: 4.4726. Min Range: -4.4726

Max Act: 4.3215. Min Act: -0.1700

Data Index: 2763356 (Open Web Text)

Max Activating Token Index: 375

Text #12

Max Range: 4.4726. Min Range: -4.4726

Max Act: 4.3088. Min Act: -0.1700

Data Index: 1722999 (Open Web Text)

Max Activating Token Index: 595

Text #13

Max Range: 4.4726. Min Range: -4.4726

Max Act: 4.2776. Min Act: -0.1700

Data Index: 6621923 (Open Web Text)

Max Activating Token Index: 825

Text #14

Max Range: 4.4726. Min Range: -4.4726

Max Act: 4.2922. Min Act: -0.1700

Data Index: 1366115 (Open Web Text)

Max Activating Token Index: 648

Text #15

Max Range: 4.4726. Min Range: -4.4726

Max Act: 4.2919. Min Act: -0.1700

Data Index: 2282438 (Open Web Text)

Max Activating Token Index: 891

Text #16

Max Range: 4.4726. Min Range: -4.4726

Max Act: 4.2553. Min Act: -0.1700

Data Index: 2998019 (Open Web Text)

Max Activating Token Index: 346

Text #17

Max Range: 4.4726. Min Range: -4.4726

Max Act: 4.2455. Min Act: -0.1700

Data Index: 7484920 (Open Web Text)

Max Activating Token Index: 92

Text #18

Max Range: 4.4726. Min Range: -4.4726

Max Act: 4.3188. Min Act: -0.1700

Data Index: 2584689 (Open Web Text)

Max Activating Token Index: 711

Text #19

Max Range: 4.4726. Min Range: -4.4726

Max Act: 4.2877. Min Act: -0.1700

Data Index: 4333511 (Open Web Text)

Max Activating Token Index: 517