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

Dataset: Open Web Text

Neuron 500 in Layer 5

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: 2.8271. Min Range: -2.8271

Max Act: 2.8032. Min Act: -0.1700

Data Index: 4489555 (Open Web Text)

Max Activating Token Index: 80

Text #1

Max Range: 2.8271. Min Range: -2.8271

Max Act: 2.8271. Min Act: -0.1700

Data Index: 7039313 (Open Web Text)

Max Activating Token Index: 599

Text #2

Max Range: 2.8271. Min Range: -2.8271

Max Act: 2.8034. Min Act: -0.1700

Data Index: 5684824 (Open Web Text)

Max Activating Token Index: 470

Text #3

Max Range: 2.8271. Min Range: -2.8271

Max Act: 2.8022. Min Act: -0.1700

Data Index: 7187945 (Open Web Text)

Max Activating Token Index: 230

Text #4

Max Range: 2.8271. Min Range: -2.8271

Max Act: 2.7912. Min Act: -0.1700

Data Index: 3210831 (Open Web Text)

Max Activating Token Index: 254

Text #5

Max Range: 2.8271. Min Range: -2.8271

Max Act: 2.7938. Min Act: -0.1700

Data Index: 3886107 (Open Web Text)

Max Activating Token Index: 128

Text #6

Max Range: 2.8271. Min Range: -2.8271

Max Act: 2.7881. Min Act: -0.1700

Data Index: 8654532 (Open Web Text)

Max Activating Token Index: 471

Text #7

Max Range: 2.8271. Min Range: -2.8271

Max Act: 2.7630. Min Act: -0.1700

Data Index: 8453616 (Open Web Text)

Max Activating Token Index: 724

Text #8

Max Range: 2.8271. Min Range: -2.8271

Max Act: 2.7718. Min Act: -0.1700

Data Index: 1198397 (Open Web Text)

Max Activating Token Index: 28

Text #9

Max Range: 2.8271. Min Range: -2.8271

Max Act: 2.7543. Min Act: -0.1700

Data Index: 3954530 (Open Web Text)

Max Activating Token Index: 686

Text #10

Max Range: 2.8271. Min Range: -2.8271

Max Act: 2.7543. Min Act: -0.1700

Data Index: 3773087 (Open Web Text)

Max Activating Token Index: 783

Text #11

Max Range: 2.8271. Min Range: -2.8271

Max Act: 2.7436. Min Act: -0.1700

Data Index: 2019350 (Open Web Text)

Max Activating Token Index: 784

Text #12

Max Range: 2.8271. Min Range: -2.8271

Max Act: 2.7401. Min Act: -0.1700

Data Index: 1901188 (Open Web Text)

Max Activating Token Index: 365

Text #13

Max Range: 2.8271. Min Range: -2.8271

Max Act: 2.7408. Min Act: -0.1700

Data Index: 6566020 (Open Web Text)

Max Activating Token Index: 596

Text #14

Max Range: 2.8271. Min Range: -2.8271

Max Act: 2.7588. Min Act: -0.1700

Data Index: 6550444 (Open Web Text)

Max Activating Token Index: 887

Text #15

Max Range: 2.8271. Min Range: -2.8271

Max Act: 2.7453. Min Act: -0.1700

Data Index: 3735019 (Open Web Text)

Max Activating Token Index: 541

Text #16

Max Range: 2.8271. Min Range: -2.8271

Max Act: 2.7232. Min Act: -0.1700

Data Index: 8412168 (Open Web Text)

Max Activating Token Index: 914

Text #17

Max Range: 2.8271. Min Range: -2.8271

Max Act: 2.7343. Min Act: -0.1700

Data Index: 8316601 (Open Web Text)

Max Activating Token Index: 996

Text #18

Max Range: 2.8271. Min Range: -2.8271

Max Act: 2.7231. Min Act: -0.1700

Data Index: 4349138 (Open Web Text)

Max Activating Token Index: 72

Text #19

Max Range: 2.8271. Min Range: -2.8271

Max Act: 2.6785. Min Act: -0.1700

Data Index: 1163972 (Open Web Text)

Max Activating Token Index: 719