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

Dataset: Open Web Text

Neuron 354 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: 4.0518. Min Range: -4.0518

Max Act: 4.0518. Min Act: -0.1700

Data Index: 6601984 (Open Web Text)

Max Activating Token Index: 212

Text #1

Max Range: 4.0518. Min Range: -4.0518

Max Act: 3.9998. Min Act: -0.1700

Data Index: 6601982 (Open Web Text)

Max Activating Token Index: 1010

Text #2

Max Range: 4.0518. Min Range: -4.0518

Max Act: 3.9460. Min Act: -0.1700

Data Index: 1210694 (Open Web Text)

Max Activating Token Index: 72

Text #3

Max Range: 4.0518. Min Range: -4.0518

Max Act: 3.9350. Min Act: -0.1700

Data Index: 5789574 (Open Web Text)

Max Activating Token Index: 149

Text #4

Max Range: 4.0518. Min Range: -4.0518

Max Act: 3.9184. Min Act: -0.1700

Data Index: 6503863 (Open Web Text)

Max Activating Token Index: 710

Text #5

Max Range: 4.0518. Min Range: -4.0518

Max Act: 3.8873. Min Act: -0.1700

Data Index: 1676218 (Open Web Text)

Max Activating Token Index: 300

Text #6

Max Range: 4.0518. Min Range: -4.0518

Max Act: 3.9008. Min Act: -0.1700

Data Index: 2094434 (Open Web Text)

Max Activating Token Index: 964

Text #7

Max Range: 4.0518. Min Range: -4.0518

Max Act: 3.8292. Min Act: -0.1700

Data Index: 2194673 (Open Web Text)

Max Activating Token Index: 749

Text #8

Max Range: 4.0518. Min Range: -4.0518

Max Act: 3.8045. Min Act: -0.1700

Data Index: 8469347 (Open Web Text)

Max Activating Token Index: 218

Text #9

Max Range: 4.0518. Min Range: -4.0518

Max Act: 3.8515. Min Act: -0.1700

Data Index: 3477162 (Open Web Text)

Max Activating Token Index: 500

Text #10

Max Range: 4.0518. Min Range: -4.0518

Max Act: 3.8206. Min Act: -0.1700

Data Index: 8798520 (Open Web Text)

Max Activating Token Index: 92

Text #11

Max Range: 4.0518. Min Range: -4.0518

Max Act: 3.8367. Min Act: -0.1700

Data Index: 6696152 (Open Web Text)

Max Activating Token Index: 540

Text #12

Max Range: 4.0518. Min Range: -4.0518

Max Act: 3.8508. Min Act: -0.1700

Data Index: 4937429 (Open Web Text)

Max Activating Token Index: 431

Text #13

Max Range: 4.0518. Min Range: -4.0518

Max Act: 3.7999. Min Act: -0.1700

Data Index: 5280158 (Open Web Text)

Max Activating Token Index: 10

Text #14

Max Range: 4.0518. Min Range: -4.0518

Max Act: 3.7889. Min Act: -0.1700

Data Index: 6200678 (Open Web Text)

Max Activating Token Index: 95

Text #15

Max Range: 4.0518. Min Range: -4.0518

Max Act: 3.7972. Min Act: -0.1700

Data Index: 4478877 (Open Web Text)

Max Activating Token Index: 119

Text #16

Max Range: 4.0518. Min Range: -4.0518

Max Act: 3.7928. Min Act: -0.1700

Data Index: 2472982 (Open Web Text)

Max Activating Token Index: 687

Text #17

Max Range: 4.0518. Min Range: -4.0518

Max Act: 3.7957. Min Act: -0.1700

Data Index: 2220061 (Open Web Text)

Max Activating Token Index: 411

Text #18

Max Range: 4.0518. Min Range: -4.0518

Max Act: 3.7640. Min Act: -0.1700

Data Index: 522499 (Open Web Text)

Max Activating Token Index: 313

Text #19

Max Range: 4.0518. Min Range: -4.0518

Max Act: 3.7596. Min Act: -0.1700

Data Index: 112516 (Open Web Text)

Max Activating Token Index: 139