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

Dataset: Open Web Text

Neuron 2897 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: 3.6729. Min Range: -3.6729

Max Act: 3.6729. Min Act: -0.1700

Data Index: 8785348 (Open Web Text)

Max Activating Token Index: 138

Text #1

Max Range: 3.6729. Min Range: -3.6729

Max Act: 3.4888. Min Act: -0.1700

Data Index: 620070 (Open Web Text)

Max Activating Token Index: 892

Text #2

Max Range: 3.6729. Min Range: -3.6729

Max Act: 3.4810. Min Act: -0.1700

Data Index: 6107381 (Open Web Text)

Max Activating Token Index: 797

Text #3

Max Range: 3.6729. Min Range: -3.6729

Max Act: 3.5047. Min Act: -0.1700

Data Index: 6065667 (Open Web Text)

Max Activating Token Index: 873

Text #4

Max Range: 3.6729. Min Range: -3.6729

Max Act: 3.4766. Min Act: -0.1700

Data Index: 524279 (Open Web Text)

Max Activating Token Index: 227

Text #5

Max Range: 3.6729. Min Range: -3.6729

Max Act: 3.4593. Min Act: -0.1700

Data Index: 3871787 (Open Web Text)

Max Activating Token Index: 952

Text #6

Max Range: 3.6729. Min Range: -3.6729

Max Act: 3.4796. Min Act: -0.1700

Data Index: 3114300 (Open Web Text)

Max Activating Token Index: 345

Text #7

Max Range: 3.6729. Min Range: -3.6729

Max Act: 3.4655. Min Act: -0.1700

Data Index: 5038111 (Open Web Text)

Max Activating Token Index: 313

Text #8

Max Range: 3.6729. Min Range: -3.6729

Max Act: 3.4869. Min Act: -0.1700

Data Index: 8097088 (Open Web Text)

Max Activating Token Index: 193

Text #9

Max Range: 3.6729. Min Range: -3.6729

Max Act: 3.4374. Min Act: -0.1700

Data Index: 1409749 (Open Web Text)

Max Activating Token Index: 588

Text #10

Max Range: 3.6729. Min Range: -3.6729

Max Act: 3.4408. Min Act: -0.1700

Data Index: 4038561 (Open Web Text)

Max Activating Token Index: 155

Text #11

Max Range: 3.6729. Min Range: -3.6729

Max Act: 3.4494. Min Act: -0.1700

Data Index: 3469902 (Open Web Text)

Max Activating Token Index: 563

Text #12

Max Range: 3.6729. Min Range: -3.6729

Max Act: 3.4399. Min Act: -0.1700

Data Index: 5521786 (Open Web Text)

Max Activating Token Index: 16

Text #13

Max Range: 3.6729. Min Range: -3.6729

Max Act: 3.4465. Min Act: -0.1700

Data Index: 6555612 (Open Web Text)

Max Activating Token Index: 493

Text #14

Max Range: 3.6729. Min Range: -3.6729

Max Act: 3.4322. Min Act: -0.1700

Data Index: 6345939 (Open Web Text)

Max Activating Token Index: 768

Text #15

Max Range: 3.6729. Min Range: -3.6729

Max Act: 3.4191. Min Act: -0.1700

Data Index: 381919 (Open Web Text)

Max Activating Token Index: 179

Text #16

Max Range: 3.6729. Min Range: -3.6729

Max Act: 3.4005. Min Act: -0.1700

Data Index: 8304031 (Open Web Text)

Max Activating Token Index: 678

Text #17

Max Range: 3.6729. Min Range: -3.6729

Max Act: 3.4128. Min Act: -0.1700

Data Index: 3785678 (Open Web Text)

Max Activating Token Index: 280

Text #18

Max Range: 3.6729. Min Range: -3.6729

Max Act: 3.3985. Min Act: -0.1700

Data Index: 4375523 (Open Web Text)

Max Activating Token Index: 474

Text #19

Max Range: 3.6729. Min Range: -3.6729

Max Act: 3.4209. Min Act: -0.1700

Data Index: 7644431 (Open Web Text)

Max Activating Token Index: 109