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

Dataset: Open Web Text

Neuron 2540 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: 3.0157. Min Range: -3.0157

Max Act: 3.0157. Min Act: -0.1700

Data Index: 1337548 (Open Web Text)

Max Activating Token Index: 404

Text #1

Max Range: 3.0157. Min Range: -3.0157

Max Act: 2.9595. Min Act: -0.1700

Data Index: 8661516 (Open Web Text)

Max Activating Token Index: 371

Text #2

Max Range: 3.0157. Min Range: -3.0157

Max Act: 2.9845. Min Act: -0.1700

Data Index: 7153382 (Open Web Text)

Max Activating Token Index: 128

Text #3

Max Range: 3.0157. Min Range: -3.0157

Max Act: 2.9477. Min Act: -0.1700

Data Index: 3573691 (Open Web Text)

Max Activating Token Index: 177

Text #4

Max Range: 3.0157. Min Range: -3.0157

Max Act: 2.9449. Min Act: -0.1700

Data Index: 4128298 (Open Web Text)

Max Activating Token Index: 600

Text #5

Max Range: 3.0157. Min Range: -3.0157

Max Act: 2.9341. Min Act: -0.1700

Data Index: 3242717 (Open Web Text)

Max Activating Token Index: 356

Text #6

Max Range: 3.0157. Min Range: -3.0157

Max Act: 2.9067. Min Act: -0.1700

Data Index: 2532221 (Open Web Text)

Max Activating Token Index: 264

Text #7

Max Range: 3.0157. Min Range: -3.0157

Max Act: 2.8977. Min Act: -0.1700

Data Index: 4838409 (Open Web Text)

Max Activating Token Index: 276

Text #8

Max Range: 3.0157. Min Range: -3.0157

Max Act: 2.8891. Min Act: -0.1700

Data Index: 7745944 (Open Web Text)

Max Activating Token Index: 773

Text #9

Max Range: 3.0157. Min Range: -3.0157

Max Act: 2.8669. Min Act: -0.1700

Data Index: 1093776 (Open Web Text)

Max Activating Token Index: 72

Text #10

Max Range: 3.0157. Min Range: -3.0157

Max Act: 2.8868. Min Act: -0.1700

Data Index: 5178176 (Open Web Text)

Max Activating Token Index: 735

Text #11

Max Range: 3.0157. Min Range: -3.0157

Max Act: 2.8525. Min Act: -0.1700

Data Index: 6764312 (Open Web Text)

Max Activating Token Index: 20

Text #12

Max Range: 3.0157. Min Range: -3.0157

Max Act: 2.8307. Min Act: -0.1700

Data Index: 5920749 (Open Web Text)

Max Activating Token Index: 59

Text #13

Max Range: 3.0157. Min Range: -3.0157

Max Act: 2.8328. Min Act: -0.1700

Data Index: 6889563 (Open Web Text)

Max Activating Token Index: 719

Text #14

Max Range: 3.0157. Min Range: -3.0157

Max Act: 2.8263. Min Act: -0.1700

Data Index: 6681930 (Open Web Text)

Max Activating Token Index: 511

Text #15

Max Range: 3.0157. Min Range: -3.0157

Max Act: 2.8230. Min Act: -0.1700

Data Index: 5813042 (Open Web Text)

Max Activating Token Index: 245

Text #16

Max Range: 3.0157. Min Range: -3.0157

Max Act: 2.7956. Min Act: -0.1700

Data Index: 7967456 (Open Web Text)

Max Activating Token Index: 255

Text #17

Max Range: 3.0157. Min Range: -3.0157

Max Act: 2.7997. Min Act: -0.1700

Data Index: 500148 (Open Web Text)

Max Activating Token Index: 15

Text #18

Max Range: 3.0157. Min Range: -3.0157

Max Act: 2.8076. Min Act: -0.1700

Data Index: 741059 (Open Web Text)

Max Activating Token Index: 966

Text #19

Max Range: 3.0157. Min Range: -3.0157

Max Act: 2.7973. Min Act: -0.1700

Data Index: 1841784 (Open Web Text)

Max Activating Token Index: 1023