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

Dataset: Open Web Text

Neuron 1321 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: 3.7469. Min Range: -3.7469

Max Act: 3.7469. Min Act: -0.1700

Data Index: 6677829 (Open Web Text)

Max Activating Token Index: 960

Text #1

Max Range: 3.7469. Min Range: -3.7469

Max Act: 3.6331. Min Act: -0.1700

Data Index: 49483 (Open Web Text)

Max Activating Token Index: 650

Text #2

Max Range: 3.7469. Min Range: -3.7469

Max Act: 3.5674. Min Act: -0.1700

Data Index: 1412014 (Open Web Text)

Max Activating Token Index: 598

Text #3

Max Range: 3.7469. Min Range: -3.7469

Max Act: 3.5175. Min Act: -0.1700

Data Index: 7963378 (Open Web Text)

Max Activating Token Index: 782

Text #4

Max Range: 3.7469. Min Range: -3.7469

Max Act: 3.4645. Min Act: -0.1700

Data Index: 1194360 (Open Web Text)

Max Activating Token Index: 56

Text #5

Max Range: 3.7469. Min Range: -3.7469

Max Act: 3.4615. Min Act: -0.1700

Data Index: 4795581 (Open Web Text)

Max Activating Token Index: 267

Text #6

Max Range: 3.7469. Min Range: -3.7469

Max Act: 3.3763. Min Act: -0.1700

Data Index: 3785920 (Open Web Text)

Max Activating Token Index: 978

Text #7

Max Range: 3.7469. Min Range: -3.7469

Max Act: 3.3755. Min Act: -0.1700

Data Index: 4690033 (Open Web Text)

Max Activating Token Index: 754

Text #8

Max Range: 3.7469. Min Range: -3.7469

Max Act: 3.3695. Min Act: -0.1700

Data Index: 1271267 (Open Web Text)

Max Activating Token Index: 926

Text #9

Max Range: 3.7469. Min Range: -3.7469

Max Act: 3.3494. Min Act: -0.1700

Data Index: 6602446 (Open Web Text)

Max Activating Token Index: 147

Text #10

Max Range: 3.7469. Min Range: -3.7469

Max Act: 3.3661. Min Act: -0.1700

Data Index: 5053136 (Open Web Text)

Max Activating Token Index: 242

Text #11

Max Range: 3.7469. Min Range: -3.7469

Max Act: 3.3257. Min Act: -0.1700

Data Index: 7425350 (Open Web Text)

Max Activating Token Index: 501

Text #12

Max Range: 3.7469. Min Range: -3.7469

Max Act: 3.2992. Min Act: -0.1700

Data Index: 6083326 (Open Web Text)

Max Activating Token Index: 688

Text #13

Max Range: 3.7469. Min Range: -3.7469

Max Act: 3.3322. Min Act: -0.1700

Data Index: 5561679 (Open Web Text)

Max Activating Token Index: 328

Text #14

Max Range: 3.7469. Min Range: -3.7469

Max Act: 3.3206. Min Act: -0.1700

Data Index: 3518092 (Open Web Text)

Max Activating Token Index: 404

Text #15

Max Range: 3.7469. Min Range: -3.7469

Max Act: 3.3208. Min Act: -0.1700

Data Index: 950664 (Open Web Text)

Max Activating Token Index: 796

Text #16

Max Range: 3.7469. Min Range: -3.7469

Max Act: 3.2753. Min Act: -0.1700

Data Index: 3789978 (Open Web Text)

Max Activating Token Index: 66

Text #17

Max Range: 3.7469. Min Range: -3.7469

Max Act: 3.2835. Min Act: -0.1700

Data Index: 4278329 (Open Web Text)

Max Activating Token Index: 310

Text #18

Max Range: 3.7469. Min Range: -3.7469

Max Act: 3.2614. Min Act: -0.1700

Data Index: 960023 (Open Web Text)

Max Activating Token Index: 739

Text #19

Max Range: 3.7469. Min Range: -3.7469

Max Act: 3.2911. Min Act: -0.1700

Data Index: 3902416 (Open Web Text)

Max Activating Token Index: 753