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

Dataset: Open Web Text

Neuron 1103 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: 4.0051. Min Range: -4.0051

Max Act: 4.0051. Min Act: -0.1700

Data Index: 1617458 (Open Web Text)

Max Activating Token Index: 463

Text #1

Max Range: 4.0051. Min Range: -4.0051

Max Act: 3.9938. Min Act: -0.1700

Data Index: 5756294 (Open Web Text)

Max Activating Token Index: 451

Text #2

Max Range: 4.0051. Min Range: -4.0051

Max Act: 3.9244. Min Act: -0.1700

Data Index: 5302304 (Open Web Text)

Max Activating Token Index: 51

Text #3

Max Range: 4.0051. Min Range: -4.0051

Max Act: 3.9113. Min Act: -0.1700

Data Index: 5392886 (Open Web Text)

Max Activating Token Index: 458

Text #4

Max Range: 4.0051. Min Range: -4.0051

Max Act: 3.8191. Min Act: -0.1700

Data Index: 6189009 (Open Web Text)

Max Activating Token Index: 494

Text #5

Max Range: 4.0051. Min Range: -4.0051

Max Act: 3.7950. Min Act: -0.1700

Data Index: 5152746 (Open Web Text)

Max Activating Token Index: 283

Text #6

Max Range: 4.0051. Min Range: -4.0051

Max Act: 3.7726. Min Act: -0.1700

Data Index: 2295228 (Open Web Text)

Max Activating Token Index: 195

Text #7

Max Range: 4.0051. Min Range: -4.0051

Max Act: 3.7857. Min Act: -0.1700

Data Index: 5106153 (Open Web Text)

Max Activating Token Index: 556

Text #8

Max Range: 4.0051. Min Range: -4.0051

Max Act: 3.7817. Min Act: -0.1700

Data Index: 5397921 (Open Web Text)

Max Activating Token Index: 87

Text #9

Max Range: 4.0051. Min Range: -4.0051

Max Act: 3.7809. Min Act: -0.1700

Data Index: 4011754 (Open Web Text)

Max Activating Token Index: 735

Text #10

Max Range: 4.0051. Min Range: -4.0051

Max Act: 3.7967. Min Act: -0.1700

Data Index: 869776 (Open Web Text)

Max Activating Token Index: 89

Text #11

Max Range: 4.0051. Min Range: -4.0051

Max Act: 3.7334. Min Act: -0.1700

Data Index: 5236309 (Open Web Text)

Max Activating Token Index: 517

Text #12

Max Range: 4.0051. Min Range: -4.0051

Max Act: 3.7709. Min Act: -0.1700

Data Index: 377931 (Open Web Text)

Max Activating Token Index: 192

Text #13

Max Range: 4.0051. Min Range: -4.0051

Max Act: 3.7603. Min Act: -0.1700

Data Index: 1668801 (Open Web Text)

Max Activating Token Index: 932

Text #14

Max Range: 4.0051. Min Range: -4.0051

Max Act: 3.7171. Min Act: -0.1700

Data Index: 8762749 (Open Web Text)

Max Activating Token Index: 68

Text #15

Max Range: 4.0051. Min Range: -4.0051

Max Act: 3.7399. Min Act: -0.1700

Data Index: 5302305 (Open Web Text)

Max Activating Token Index: 149

Text #16

Max Range: 4.0051. Min Range: -4.0051

Max Act: 3.7150. Min Act: -0.1700

Data Index: 6714523 (Open Web Text)

Max Activating Token Index: 961

Text #17

Max Range: 4.0051. Min Range: -4.0051

Max Act: 3.7361. Min Act: -0.1700

Data Index: 8173047 (Open Web Text)

Max Activating Token Index: 905

Text #18

Max Range: 4.0051. Min Range: -4.0051

Max Act: 3.6892. Min Act: -0.1700

Data Index: 854331 (Open Web Text)

Max Activating Token Index: 552

Text #19

Max Range: 4.0051. Min Range: -4.0051

Max Act: 3.6846. Min Act: -0.1700

Data Index: 1669271 (Open Web Text)

Max Activating Token Index: 612