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

Dataset: Open Web Text

Neuron 2375 in Layer 1

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: 4.9861. Min Range: -4.9861

Max Act: 4.9861. Min Act: -0.1700

Data Index: 197037 (Open Web Text)

Max Activating Token Index: 427

Text #1

Max Range: 4.9861. Min Range: -4.9861

Max Act: 4.9729. Min Act: -0.1700

Data Index: 3037482 (Open Web Text)

Max Activating Token Index: 246

Text #2

Max Range: 4.9861. Min Range: -4.9861

Max Act: 4.9716. Min Act: -0.1700

Data Index: 8592439 (Open Web Text)

Max Activating Token Index: 299

Text #3

Max Range: 4.9861. Min Range: -4.9861

Max Act: 4.9592. Min Act: -0.1700

Data Index: 6867497 (Open Web Text)

Max Activating Token Index: 627

Text #4

Max Range: 4.9861. Min Range: -4.9861

Max Act: 4.9598. Min Act: -0.1700

Data Index: 6606547 (Open Web Text)

Max Activating Token Index: 67

Text #5

Max Range: 4.9861. Min Range: -4.9861

Max Act: 4.9332. Min Act: -0.1700

Data Index: 6469829 (Open Web Text)

Max Activating Token Index: 442

Text #6

Max Range: 4.9861. Min Range: -4.9861

Max Act: 4.9415. Min Act: -0.1700

Data Index: 5268965 (Open Web Text)

Max Activating Token Index: 647

Text #7

Max Range: 4.9861. Min Range: -4.9861

Max Act: 4.9707. Min Act: -0.1700

Data Index: 4675473 (Open Web Text)

Max Activating Token Index: 212

Text #8

Max Range: 4.9861. Min Range: -4.9861

Max Act: 4.9677. Min Act: -0.1700

Data Index: 4329133 (Open Web Text)

Max Activating Token Index: 502

Text #9

Max Range: 4.9861. Min Range: -4.9861

Max Act: 4.9295. Min Act: -0.1700

Data Index: 1169920 (Open Web Text)

Max Activating Token Index: 620

Text #10

Max Range: 4.9861. Min Range: -4.9861

Max Act: 4.9473. Min Act: -0.1700

Data Index: 3233450 (Open Web Text)

Max Activating Token Index: 74

Text #11

Max Range: 4.9861. Min Range: -4.9861

Max Act: 4.9561. Min Act: -0.1700

Data Index: 6991880 (Open Web Text)

Max Activating Token Index: 237

Text #12

Max Range: 4.9861. Min Range: -4.9861

Max Act: 4.9292. Min Act: -0.1700

Data Index: 111411 (Open Web Text)

Max Activating Token Index: 101

Text #13

Max Range: 4.9861. Min Range: -4.9861

Max Act: 4.9247. Min Act: -0.1700

Data Index: 4379715 (Open Web Text)

Max Activating Token Index: 188

Text #14

Max Range: 4.9861. Min Range: -4.9861

Max Act: 4.9516. Min Act: -0.1699

Data Index: 4938486 (Open Web Text)

Max Activating Token Index: 643

Text #15

Max Range: 4.9861. Min Range: -4.9861

Max Act: 4.9249. Min Act: -0.1700

Data Index: 5152785 (Open Web Text)

Max Activating Token Index: 616

Text #16

Max Range: 4.9861. Min Range: -4.9861

Max Act: 4.9271. Min Act: -0.1700

Data Index: 4084225 (Open Web Text)

Max Activating Token Index: 272

Text #17

Max Range: 4.9861. Min Range: -4.9861

Max Act: 4.9231. Min Act: -0.1700

Data Index: 2667056 (Open Web Text)

Max Activating Token Index: 405

Text #18

Max Range: 4.9861. Min Range: -4.9861

Max Act: 4.9368. Min Act: -0.1700

Data Index: 5886664 (Open Web Text)

Max Activating Token Index: 38

Text #19

Max Range: 4.9861. Min Range: -4.9861

Max Act: 4.9101. Min Act: -0.1700

Data Index: 5888520 (Open Web Text)

Max Activating Token Index: 224