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

Dataset: Open Web Text

Neuron 885 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: 3.4036. Min Range: -3.4036

Max Act: 3.4036. Min Act: -0.1700

Data Index: 2964554 (Open Web Text)

Max Activating Token Index: 908

Text #1

Max Range: 3.4036. Min Range: -3.4036

Max Act: 3.3795. Min Act: -0.1700

Data Index: 8535571 (Open Web Text)

Max Activating Token Index: 561

Text #2

Max Range: 3.4036. Min Range: -3.4036

Max Act: 3.3546. Min Act: -0.1700

Data Index: 4397469 (Open Web Text)

Max Activating Token Index: 915

Text #3

Max Range: 3.4036. Min Range: -3.4036

Max Act: 3.3317. Min Act: -0.1700

Data Index: 1105323 (Open Web Text)

Max Activating Token Index: 105

Text #4

Max Range: 3.4036. Min Range: -3.4036

Max Act: 3.3331. Min Act: -0.1700

Data Index: 4146390 (Open Web Text)

Max Activating Token Index: 586

Text #5

Max Range: 3.4036. Min Range: -3.4036

Max Act: 3.3295. Min Act: -0.1700

Data Index: 7491153 (Open Web Text)

Max Activating Token Index: 770

Text #6

Max Range: 3.4036. Min Range: -3.4036

Max Act: 3.3437. Min Act: -0.1700

Data Index: 8524627 (Open Web Text)

Max Activating Token Index: 576

Text #7

Max Range: 3.4036. Min Range: -3.4036

Max Act: 3.3142. Min Act: -0.1700

Data Index: 8753579 (Open Web Text)

Max Activating Token Index: 254

Text #8

Max Range: 3.4036. Min Range: -3.4036

Max Act: 3.2990. Min Act: -0.1700

Data Index: 2233870 (Open Web Text)

Max Activating Token Index: 69

Text #9

Max Range: 3.4036. Min Range: -3.4036

Max Act: 3.3144. Min Act: -0.1700

Data Index: 4674662 (Open Web Text)

Max Activating Token Index: 50

Text #10

Max Range: 3.4036. Min Range: -3.4036

Max Act: 3.3046. Min Act: -0.1700

Data Index: 4018006 (Open Web Text)

Max Activating Token Index: 392

Text #11

Max Range: 3.4036. Min Range: -3.4036

Max Act: 3.3051. Min Act: -0.1700

Data Index: 4446910 (Open Web Text)

Max Activating Token Index: 300

Text #12

Max Range: 3.4036. Min Range: -3.4036

Max Act: 3.3150. Min Act: -0.1700

Data Index: 1697587 (Open Web Text)

Max Activating Token Index: 1013

Text #13

Max Range: 3.4036. Min Range: -3.4036

Max Act: 3.2903. Min Act: -0.1700

Data Index: 4023470 (Open Web Text)

Max Activating Token Index: 574

Text #14

Max Range: 3.4036. Min Range: -3.4036

Max Act: 3.2971. Min Act: -0.1700

Data Index: 8168655 (Open Web Text)

Max Activating Token Index: 415

Text #15

Max Range: 3.4036. Min Range: -3.4036

Max Act: 3.2940. Min Act: -0.1700

Data Index: 6516489 (Open Web Text)

Max Activating Token Index: 627

Text #16

Max Range: 3.4036. Min Range: -3.4036

Max Act: 3.2875. Min Act: -0.1700

Data Index: 2894480 (Open Web Text)

Max Activating Token Index: 82

Text #17

Max Range: 3.4036. Min Range: -3.4036

Max Act: 3.2837. Min Act: -0.1700

Data Index: 4847688 (Open Web Text)

Max Activating Token Index: 828

Text #18

Max Range: 3.4036. Min Range: -3.4036

Max Act: 3.2815. Min Act: -0.1700

Data Index: 2057037 (Open Web Text)

Max Activating Token Index: 735

Text #19

Max Range: 3.4036. Min Range: -3.4036

Max Act: 3.2759. Min Act: -0.1700

Data Index: 6450722 (Open Web Text)

Max Activating Token Index: 358