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

Dataset: Open Web Text

Neuron 2849 in Layer 6

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: 3.9673. Min Range: -3.9673

Max Act: 3.9673. Min Act: -0.1700

Data Index: 8024261 (Open Web Text)

Max Activating Token Index: 107

Text #1

Max Range: 3.9673. Min Range: -3.9673

Max Act: 3.9622. Min Act: -0.1700

Data Index: 3692679 (Open Web Text)

Max Activating Token Index: 156

Text #2

Max Range: 3.9673. Min Range: -3.9673

Max Act: 3.8958. Min Act: -0.1700

Data Index: 5361978 (Open Web Text)

Max Activating Token Index: 216

Text #3

Max Range: 3.9673. Min Range: -3.9673

Max Act: 3.9262. Min Act: -0.1700

Data Index: 6561634 (Open Web Text)

Max Activating Token Index: 62

Text #4

Max Range: 3.9673. Min Range: -3.9673

Max Act: 3.8560. Min Act: -0.1700

Data Index: 2763967 (Open Web Text)

Max Activating Token Index: 346

Text #5

Max Range: 3.9673. Min Range: -3.9673

Max Act: 3.8533. Min Act: -0.1700

Data Index: 8338507 (Open Web Text)

Max Activating Token Index: 138

Text #6

Max Range: 3.9673. Min Range: -3.9673

Max Act: 3.8272. Min Act: -0.1700

Data Index: 4743457 (Open Web Text)

Max Activating Token Index: 167

Text #7

Max Range: 3.9673. Min Range: -3.9673

Max Act: 3.8106. Min Act: -0.1700

Data Index: 1898377 (Open Web Text)

Max Activating Token Index: 189

Text #8

Max Range: 3.9673. Min Range: -3.9673

Max Act: 3.8363. Min Act: -0.1700

Data Index: 5580056 (Open Web Text)

Max Activating Token Index: 435

Text #9

Max Range: 3.9673. Min Range: -3.9673

Max Act: 3.8428. Min Act: -0.1700

Data Index: 8802810 (Open Web Text)

Max Activating Token Index: 502

Text #10

Max Range: 3.9673. Min Range: -3.9673

Max Act: 3.7949. Min Act: -0.1700

Data Index: 2592700 (Open Web Text)

Max Activating Token Index: 33

Text #11

Max Range: 3.9673. Min Range: -3.9673

Max Act: 3.7815. Min Act: -0.1700

Data Index: 5318986 (Open Web Text)

Max Activating Token Index: 127

Text #12

Max Range: 3.9673. Min Range: -3.9673

Max Act: 3.7678. Min Act: -0.1700

Data Index: 7400735 (Open Web Text)

Max Activating Token Index: 72

Text #13

Max Range: 3.9673. Min Range: -3.9673

Max Act: 3.7405. Min Act: -0.1700

Data Index: 4214315 (Open Web Text)

Max Activating Token Index: 59

Text #14

Max Range: 3.9673. Min Range: -3.9673

Max Act: 3.7066. Min Act: -0.1700

Data Index: 6250964 (Open Web Text)

Max Activating Token Index: 230

Text #15

Max Range: 3.9673. Min Range: -3.9673

Max Act: 3.7088. Min Act: -0.1700

Data Index: 3976961 (Open Web Text)

Max Activating Token Index: 682

Text #16

Max Range: 3.9673. Min Range: -3.9673

Max Act: 3.7191. Min Act: -0.1700

Data Index: 8480718 (Open Web Text)

Max Activating Token Index: 550

Text #17

Max Range: 3.9673. Min Range: -3.9673

Max Act: 3.7068. Min Act: -0.1700

Data Index: 8789817 (Open Web Text)

Max Activating Token Index: 454

Text #18

Max Range: 3.9673. Min Range: -3.9673

Max Act: 3.6791. Min Act: -0.1700

Data Index: 4410932 (Open Web Text)

Max Activating Token Index: 665

Text #19

Max Range: 3.9673. Min Range: -3.9673

Max Act: 3.7195. Min Act: -0.1700

Data Index: 470477 (Open Web Text)

Max Activating Token Index: 907