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

Dataset: Open Web Text

Neuron 1127 in Layer 1

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: 1.7229. Min Range: -1.7229

Max Act: 1.7229. Min Act: -0.1700

Data Index: 5059828 (Open Web Text)

Max Activating Token Index: 101

Text #1

Max Range: 1.7229. Min Range: -1.7229

Max Act: 1.7209. Min Act: -0.1700

Data Index: 238301 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 1.7229. Min Range: -1.7229

Max Act: 1.7032. Min Act: -0.1700

Data Index: 8553450 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 1.7229. Min Range: -1.7229

Max Act: 1.6909. Min Act: -0.1700

Data Index: 524697 (Open Web Text)

Max Activating Token Index: 8

Text #4

Max Range: 1.7229. Min Range: -1.7229

Max Act: 1.6886. Min Act: -0.1700

Data Index: 238503 (Open Web Text)

Max Activating Token Index: 201

Text #5

Max Range: 1.7229. Min Range: -1.7229

Max Act: 1.6857. Min Act: -0.1700

Data Index: 975870 (Open Web Text)

Max Activating Token Index: 78

Text #6

Max Range: 1.7229. Min Range: -1.7229

Max Act: 1.6723. Min Act: -0.1700

Data Index: 3424848 (Open Web Text)

Max Activating Token Index: 105

Text #7

Max Range: 1.7229. Min Range: -1.7229

Max Act: 1.6766. Min Act: -0.1700

Data Index: 6980110 (Open Web Text)

Max Activating Token Index: 103

Text #8

Max Range: 1.7229. Min Range: -1.7229

Max Act: 1.6768. Min Act: -0.1700

Data Index: 8382894 (Open Web Text)

Max Activating Token Index: 948

Text #9

Max Range: 1.7229. Min Range: -1.7229

Max Act: 1.6637. Min Act: -0.1700

Data Index: 5190767 (Open Web Text)

Max Activating Token Index: 88

Text #10

Max Range: 1.7229. Min Range: -1.7229

Max Act: 1.6767. Min Act: -0.1700

Data Index: 7447968 (Open Web Text)

Max Activating Token Index: 459

Text #11

Max Range: 1.7229. Min Range: -1.7229

Max Act: 1.6722. Min Act: -0.1700

Data Index: 4061296 (Open Web Text)

Max Activating Token Index: 10

Text #12

Max Range: 1.7229. Min Range: -1.7229

Max Act: 1.6587. Min Act: -0.1700

Data Index: 8299361 (Open Web Text)

Max Activating Token Index: 304

Text #13

Max Range: 1.7229. Min Range: -1.7229

Max Act: 1.6561. Min Act: -0.1700

Data Index: 1886053 (Open Web Text)

Max Activating Token Index: 9

Text #14

Max Range: 1.7229. Min Range: -1.7229

Max Act: 1.6680. Min Act: -0.1700

Data Index: 6933182 (Open Web Text)

Max Activating Token Index: 14

Text #15

Max Range: 1.7229. Min Range: -1.7229

Max Act: 1.6544. Min Act: -0.1700

Data Index: 8341693 (Open Web Text)

Max Activating Token Index: 140

Text #16

Max Range: 1.7229. Min Range: -1.7229

Max Act: 1.6547. Min Act: -0.1700

Data Index: 5511473 (Open Web Text)

Max Activating Token Index: 44

Text #17

Max Range: 1.7229. Min Range: -1.7229

Max Act: 1.6664. Min Act: -0.1700

Data Index: 1555976 (Open Web Text)

Max Activating Token Index: 139

Text #18

Max Range: 1.7229. Min Range: -1.7229

Max Act: 1.6482. Min Act: -0.1700

Data Index: 7127390 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 1.7229. Min Range: -1.7229

Max Act: 1.6459. Min Act: -0.1700

Data Index: 6876028 (Open Web Text)

Max Activating Token Index: 314