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

Dataset: Open Web Text

Neuron 136 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: 4.4675. Min Range: -4.4675

Max Act: 4.4675. Min Act: -0.1700

Data Index: 8704348 (Open Web Text)

Max Activating Token Index: 642

Text #1

Max Range: 4.4675. Min Range: -4.4675

Max Act: 4.3952. Min Act: -0.1700

Data Index: 8257134 (Open Web Text)

Max Activating Token Index: 133

Text #2

Max Range: 4.4675. Min Range: -4.4675

Max Act: 4.3943. Min Act: -0.1700

Data Index: 3190926 (Open Web Text)

Max Activating Token Index: 211

Text #3

Max Range: 4.4675. Min Range: -4.4675

Max Act: 4.3306. Min Act: -0.1700

Data Index: 5658467 (Open Web Text)

Max Activating Token Index: 601

Text #4

Max Range: 4.4675. Min Range: -4.4675

Max Act: 4.3153. Min Act: -0.1700

Data Index: 7022832 (Open Web Text)

Max Activating Token Index: 189

Text #5

Max Range: 4.4675. Min Range: -4.4675

Max Act: 4.3326. Min Act: -0.1700

Data Index: 3958700 (Open Web Text)

Max Activating Token Index: 930

Text #6

Max Range: 4.4675. Min Range: -4.4675

Max Act: 4.3162. Min Act: -0.1700

Data Index: 8596832 (Open Web Text)

Max Activating Token Index: 623

Text #7

Max Range: 4.4675. Min Range: -4.4675

Max Act: 4.2714. Min Act: -0.1700

Data Index: 5936589 (Open Web Text)

Max Activating Token Index: 403

Text #8

Max Range: 4.4675. Min Range: -4.4675

Max Act: 4.2653. Min Act: -0.1700

Data Index: 3074574 (Open Web Text)

Max Activating Token Index: 792

Text #9

Max Range: 4.4675. Min Range: -4.4675

Max Act: 4.2987. Min Act: -0.1700

Data Index: 7038293 (Open Web Text)

Max Activating Token Index: 819

Text #10

Max Range: 4.4675. Min Range: -4.4675

Max Act: 4.2946. Min Act: -0.1700

Data Index: 1994757 (Open Web Text)

Max Activating Token Index: 1015

Text #11

Max Range: 4.4675. Min Range: -4.4675

Max Act: 4.2713. Min Act: -0.1700

Data Index: 5651540 (Open Web Text)

Max Activating Token Index: 281

Text #12

Max Range: 4.4675. Min Range: -4.4675

Max Act: 4.3035. Min Act: -0.1700

Data Index: 404295 (Open Web Text)

Max Activating Token Index: 491

Text #13

Max Range: 4.4675. Min Range: -4.4675

Max Act: 4.2627. Min Act: -0.1700

Data Index: 7575415 (Open Web Text)

Max Activating Token Index: 285

Text #14

Max Range: 4.4675. Min Range: -4.4675

Max Act: 4.2510. Min Act: -0.1700

Data Index: 2473474 (Open Web Text)

Max Activating Token Index: 888

Text #15

Max Range: 4.4675. Min Range: -4.4675

Max Act: 4.2849. Min Act: -0.1700

Data Index: 6375649 (Open Web Text)

Max Activating Token Index: 568

Text #16

Max Range: 4.4675. Min Range: -4.4675

Max Act: 4.2754. Min Act: -0.1700

Data Index: 1930324 (Open Web Text)

Max Activating Token Index: 174

Text #17

Max Range: 4.4675. Min Range: -4.4675

Max Act: 4.2862. Min Act: -0.1700

Data Index: 5552567 (Open Web Text)

Max Activating Token Index: 969

Text #18

Max Range: 4.4675. Min Range: -4.4675

Max Act: 4.2921. Min Act: -0.1700

Data Index: 7458294 (Open Web Text)

Max Activating Token Index: 519

Text #19

Max Range: 4.4675. Min Range: -4.4675

Max Act: 4.2379. Min Act: -0.1700

Data Index: 6818884 (Open Web Text)

Max Activating Token Index: 859