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

Dataset: Open Web Text

Neuron 2901 in Layer 3

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: 4.1581. Min Range: -4.1581

Max Act: 4.1581. Min Act: -0.1700

Data Index: 3961378 (Open Web Text)

Max Activating Token Index: 81

Text #1

Max Range: 4.1581. Min Range: -4.1581

Max Act: 4.0672. Min Act: -0.1700

Data Index: 63089 (Open Web Text)

Max Activating Token Index: 765

Text #2

Max Range: 4.1581. Min Range: -4.1581

Max Act: 4.1084. Min Act: -0.1700

Data Index: 6835799 (Open Web Text)

Max Activating Token Index: 517

Text #3

Max Range: 4.1581. Min Range: -4.1581

Max Act: 4.0301. Min Act: -0.1700

Data Index: 6810895 (Open Web Text)

Max Activating Token Index: 201

Text #4

Max Range: 4.1581. Min Range: -4.1581

Max Act: 4.0154. Min Act: -0.1700

Data Index: 2140598 (Open Web Text)

Max Activating Token Index: 294

Text #5

Max Range: 4.1581. Min Range: -4.1581

Max Act: 4.0156. Min Act: -0.1700

Data Index: 7466358 (Open Web Text)

Max Activating Token Index: 399

Text #6

Max Range: 4.1581. Min Range: -4.1581

Max Act: 3.9346. Min Act: -0.1700

Data Index: 8757892 (Open Web Text)

Max Activating Token Index: 616

Text #7

Max Range: 4.1581. Min Range: -4.1581

Max Act: 4.0040. Min Act: -0.1700

Data Index: 6440532 (Open Web Text)

Max Activating Token Index: 754

Text #8

Max Range: 4.1581. Min Range: -4.1581

Max Act: 3.9433. Min Act: -0.1700

Data Index: 5303732 (Open Web Text)

Max Activating Token Index: 495

Text #9

Max Range: 4.1581. Min Range: -4.1581

Max Act: 3.9586. Min Act: -0.1700

Data Index: 8766573 (Open Web Text)

Max Activating Token Index: 213

Text #10

Max Range: 4.1581. Min Range: -4.1581

Max Act: 3.9612. Min Act: -0.1700

Data Index: 325774 (Open Web Text)

Max Activating Token Index: 94

Text #11

Max Range: 4.1581. Min Range: -4.1581

Max Act: 3.9603. Min Act: -0.1700

Data Index: 77778 (Open Web Text)

Max Activating Token Index: 188

Text #12

Max Range: 4.1581. Min Range: -4.1581

Max Act: 3.9553. Min Act: -0.1700

Data Index: 1919056 (Open Web Text)

Max Activating Token Index: 389

Text #13

Max Range: 4.1581. Min Range: -4.1581

Max Act: 3.9213. Min Act: -0.1700

Data Index: 8567910 (Open Web Text)

Max Activating Token Index: 560

Text #14

Max Range: 4.1581. Min Range: -4.1581

Max Act: 3.8992. Min Act: -0.1700

Data Index: 1618180 (Open Web Text)

Max Activating Token Index: 640

Text #15

Max Range: 4.1581. Min Range: -4.1581

Max Act: 3.9018. Min Act: -0.1700

Data Index: 8525276 (Open Web Text)

Max Activating Token Index: 912

Text #16

Max Range: 4.1581. Min Range: -4.1581

Max Act: 3.9131. Min Act: -0.1700

Data Index: 134541 (Open Web Text)

Max Activating Token Index: 653

Text #17

Max Range: 4.1581. Min Range: -4.1581

Max Act: 3.9072. Min Act: -0.1700

Data Index: 6952106 (Open Web Text)

Max Activating Token Index: 988

Text #18

Max Range: 4.1581. Min Range: -4.1581

Max Act: 3.8708. Min Act: -0.1700

Data Index: 3716338 (Open Web Text)

Max Activating Token Index: 574

Text #19

Max Range: 4.1581. Min Range: -4.1581

Max Act: 3.8863. Min Act: -0.1700

Data Index: 7548192 (Open Web Text)

Max Activating Token Index: 25