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

Dataset: Open Web Text

Neuron 1 in Layer 2

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: 4.6044. Min Range: -4.6044

Max Act: 4.6044. Min Act: -0.1700

Data Index: 1332212 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 4.6044. Min Range: -4.6044

Max Act: 4.4621. Min Act: -0.1700

Data Index: 3154676 (Open Web Text)

Max Activating Token Index: 430

Text #2

Max Range: 4.6044. Min Range: -4.6044

Max Act: 4.4707. Min Act: -0.1700

Data Index: 6158375 (Open Web Text)

Max Activating Token Index: 853

Text #3

Max Range: 4.6044. Min Range: -4.6044

Max Act: 4.4366. Min Act: -0.1700

Data Index: 4172067 (Open Web Text)

Max Activating Token Index: 143

Text #4

Max Range: 4.6044. Min Range: -4.6044

Max Act: 4.3534. Min Act: -0.1700

Data Index: 4756175 (Open Web Text)

Max Activating Token Index: 588

Text #5

Max Range: 4.6044. Min Range: -4.6044

Max Act: 4.3527. Min Act: -0.1700

Data Index: 7824801 (Open Web Text)

Max Activating Token Index: 607

Text #6

Max Range: 4.6044. Min Range: -4.6044

Max Act: 4.3921. Min Act: -0.1700

Data Index: 2131446 (Open Web Text)

Max Activating Token Index: 988

Text #7

Max Range: 4.6044. Min Range: -4.6044

Max Act: 4.3666. Min Act: -0.1700

Data Index: 7800451 (Open Web Text)

Max Activating Token Index: 627

Text #8

Max Range: 4.6044. Min Range: -4.6044

Max Act: 4.3863. Min Act: -0.1700

Data Index: 4427646 (Open Web Text)

Max Activating Token Index: 586

Text #9

Max Range: 4.6044. Min Range: -4.6044

Max Act: 4.3727. Min Act: -0.1700

Data Index: 1978107 (Open Web Text)

Max Activating Token Index: 248

Text #10

Max Range: 4.6044. Min Range: -4.6044

Max Act: 4.3813. Min Act: -0.1700

Data Index: 3086987 (Open Web Text)

Max Activating Token Index: 653

Text #11

Max Range: 4.6044. Min Range: -4.6044

Max Act: 4.3749. Min Act: -0.1700

Data Index: 8204314 (Open Web Text)

Max Activating Token Index: 325

Text #12

Max Range: 4.6044. Min Range: -4.6044

Max Act: 4.3183. Min Act: -0.1700

Data Index: 6629738 (Open Web Text)

Max Activating Token Index: 245

Text #13

Max Range: 4.6044. Min Range: -4.6044

Max Act: 4.3476. Min Act: -0.1700

Data Index: 6098081 (Open Web Text)

Max Activating Token Index: 429

Text #14

Max Range: 4.6044. Min Range: -4.6044

Max Act: 4.3586. Min Act: -0.1700

Data Index: 3921315 (Open Web Text)

Max Activating Token Index: 582

Text #15

Max Range: 4.6044. Min Range: -4.6044

Max Act: 4.3424. Min Act: -0.1700

Data Index: 3444249 (Open Web Text)

Max Activating Token Index: 79

Text #16

Max Range: 4.6044. Min Range: -4.6044

Max Act: 4.3482. Min Act: -0.1700

Data Index: 4516178 (Open Web Text)

Max Activating Token Index: 504

Text #17

Max Range: 4.6044. Min Range: -4.6044

Max Act: 4.3567. Min Act: -0.1700

Data Index: 5808834 (Open Web Text)

Max Activating Token Index: 578

Text #18

Max Range: 4.6044. Min Range: -4.6044

Max Act: 4.3472. Min Act: -0.1700

Data Index: 5760230 (Open Web Text)

Max Activating Token Index: 314

Text #19

Max Range: 4.6044. Min Range: -4.6044

Max Act: 4.3466. Min Act: -0.1700

Data Index: 4913711 (Open Web Text)

Max Activating Token Index: 613