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

Dataset: Open Web Text

Neuron 2757 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: 2.8276. Min Range: -2.8276

Max Act: 2.8276. Min Act: -0.1700

Data Index: 7354009 (Open Web Text)

Max Activating Token Index: 764

Text #1

Max Range: 2.8276. Min Range: -2.8276

Max Act: 2.7207. Min Act: -0.1700

Data Index: 4345186 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 2.8276. Min Range: -2.8276

Max Act: 2.7488. Min Act: -0.1700

Data Index: 2237131 (Open Web Text)

Max Activating Token Index: 10

Text #3

Max Range: 2.8276. Min Range: -2.8276

Max Act: 2.7201. Min Act: -0.1700

Data Index: 8558076 (Open Web Text)

Max Activating Token Index: 450

Text #4

Max Range: 2.8276. Min Range: -2.8276

Max Act: 2.6966. Min Act: -0.1700

Data Index: 1305205 (Open Web Text)

Max Activating Token Index: 480

Text #5

Max Range: 2.8276. Min Range: -2.8276

Max Act: 2.6997. Min Act: -0.1700

Data Index: 5110082 (Open Web Text)

Max Activating Token Index: 673

Text #6

Max Range: 2.8276. Min Range: -2.8276

Max Act: 2.6904. Min Act: -0.1700

Data Index: 2755151 (Open Web Text)

Max Activating Token Index: 522

Text #7

Max Range: 2.8276. Min Range: -2.8276

Max Act: 2.6764. Min Act: -0.1700

Data Index: 3881387 (Open Web Text)

Max Activating Token Index: 902

Text #8

Max Range: 2.8276. Min Range: -2.8276

Max Act: 2.7042. Min Act: -0.1700

Data Index: 4691409 (Open Web Text)

Max Activating Token Index: 765

Text #9

Max Range: 2.8276. Min Range: -2.8276

Max Act: 2.6729. Min Act: -0.1700

Data Index: 1738037 (Open Web Text)

Max Activating Token Index: 1019

Text #10

Max Range: 2.8276. Min Range: -2.8276

Max Act: 2.6443. Min Act: -0.1700

Data Index: 1572625 (Open Web Text)

Max Activating Token Index: 448

Text #11

Max Range: 2.8276. Min Range: -2.8276

Max Act: 2.6794. Min Act: -0.1700

Data Index: 7487200 (Open Web Text)

Max Activating Token Index: 444

Text #12

Max Range: 2.8276. Min Range: -2.8276

Max Act: 2.6310. Min Act: -0.1700

Data Index: 3975055 (Open Web Text)

Max Activating Token Index: 430

Text #13

Max Range: 2.8276. Min Range: -2.8276

Max Act: 2.6670. Min Act: -0.1700

Data Index: 7101636 (Open Web Text)

Max Activating Token Index: 480

Text #14

Max Range: 2.8276. Min Range: -2.8276

Max Act: 2.6393. Min Act: -0.1700

Data Index: 5370094 (Open Web Text)

Max Activating Token Index: 909

Text #15

Max Range: 2.8276. Min Range: -2.8276

Max Act: 2.6206. Min Act: -0.1700

Data Index: 5752173 (Open Web Text)

Max Activating Token Index: 166

Text #16

Max Range: 2.8276. Min Range: -2.8276

Max Act: 2.6411. Min Act: -0.1700

Data Index: 4705090 (Open Web Text)

Max Activating Token Index: 358

Text #17

Max Range: 2.8276. Min Range: -2.8276

Max Act: 2.6153. Min Act: -0.1700

Data Index: 7743422 (Open Web Text)

Max Activating Token Index: 676

Text #18

Max Range: 2.8276. Min Range: -2.8276

Max Act: 2.6416. Min Act: -0.1700

Data Index: 1409857 (Open Web Text)

Max Activating Token Index: 354

Text #19

Max Range: 2.8276. Min Range: -2.8276

Max Act: 2.6414. Min Act: -0.1700

Data Index: 3704811 (Open Web Text)

Max Activating Token Index: 859