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

Dataset: Open Web Text

Neuron 388 in Layer 4

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: 3.8712. Min Range: -3.8712

Max Act: 3.8712. Min Act: -0.1700

Data Index: 8468106 (Open Web Text)

Max Activating Token Index: 960

Text #1

Max Range: 3.8712. Min Range: -3.8712

Max Act: 3.8416. Min Act: -0.1700

Data Index: 6306504 (Open Web Text)

Max Activating Token Index: 562

Text #2

Max Range: 3.8712. Min Range: -3.8712

Max Act: 3.8288. Min Act: -0.1700

Data Index: 6878492 (Open Web Text)

Max Activating Token Index: 482

Text #3

Max Range: 3.8712. Min Range: -3.8712

Max Act: 3.8243. Min Act: -0.1700

Data Index: 7342014 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 3.8712. Min Range: -3.8712

Max Act: 3.7956. Min Act: -0.1700

Data Index: 3431561 (Open Web Text)

Max Activating Token Index: 69

Text #5

Max Range: 3.8712. Min Range: -3.8712

Max Act: 3.8102. Min Act: -0.1700

Data Index: 4991933 (Open Web Text)

Max Activating Token Index: 476

Text #6

Max Range: 3.8712. Min Range: -3.8712

Max Act: 3.7641. Min Act: -0.1700

Data Index: 4349499 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 3.8712. Min Range: -3.8712

Max Act: 3.7624. Min Act: -0.1700

Data Index: 1905672 (Open Web Text)

Max Activating Token Index: 112

Text #8

Max Range: 3.8712. Min Range: -3.8712

Max Act: 3.7488. Min Act: -0.1700

Data Index: 2899248 (Open Web Text)

Max Activating Token Index: 584

Text #9

Max Range: 3.8712. Min Range: -3.8712

Max Act: 3.7444. Min Act: -0.1700

Data Index: 5850365 (Open Web Text)

Max Activating Token Index: 326

Text #10

Max Range: 3.8712. Min Range: -3.8712

Max Act: 3.7400. Min Act: -0.1700

Data Index: 6272389 (Open Web Text)

Max Activating Token Index: 976

Text #11

Max Range: 3.8712. Min Range: -3.8712

Max Act: 3.7358. Min Act: -0.1700

Data Index: 3609756 (Open Web Text)

Max Activating Token Index: 482

Text #12

Max Range: 3.8712. Min Range: -3.8712

Max Act: 3.7203. Min Act: -0.1700

Data Index: 4298846 (Open Web Text)

Max Activating Token Index: 412

Text #13

Max Range: 3.8712. Min Range: -3.8712

Max Act: 3.7387. Min Act: -0.1700

Data Index: 2135740 (Open Web Text)

Max Activating Token Index: 424

Text #14

Max Range: 3.8712. Min Range: -3.8712

Max Act: 3.7255. Min Act: -0.1700

Data Index: 6005869 (Open Web Text)

Max Activating Token Index: 14

Text #15

Max Range: 3.8712. Min Range: -3.8712

Max Act: 3.6951. Min Act: -0.1700

Data Index: 5977554 (Open Web Text)

Max Activating Token Index: 584

Text #16

Max Range: 3.8712. Min Range: -3.8712

Max Act: 3.7099. Min Act: -0.1700

Data Index: 528674 (Open Web Text)

Max Activating Token Index: 926

Text #17

Max Range: 3.8712. Min Range: -3.8712

Max Act: 3.7119. Min Act: -0.1700

Data Index: 4704447 (Open Web Text)

Max Activating Token Index: 296

Text #18

Max Range: 3.8712. Min Range: -3.8712

Max Act: 3.6857. Min Act: -0.1700

Data Index: 6703373 (Open Web Text)

Max Activating Token Index: 511

Text #19

Max Range: 3.8712. Min Range: -3.8712

Max Act: 3.7044. Min Act: -0.1700

Data Index: 6593162 (Open Web Text)

Max Activating Token Index: 426