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

Dataset: Open Web Text

Neuron 2701 in Layer 0

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: 1.4962. Min Range: -1.4962

Max Act: 1.4962. Min Act: -0.1171

Data Index: 3230436 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 1.4962. Min Range: -1.4962

Max Act: 1.4927. Min Act: -0.0612

Data Index: 706382 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 1.4962. Min Range: -1.4962

Max Act: 1.4642. Min Act: -0.0482

Data Index: 3001556 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 1.4962. Min Range: -1.4962

Max Act: 1.4642. Min Act: -0.0756

Data Index: 730924 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 1.4962. Min Range: -1.4962

Max Act: 1.4642. Min Act: -0.0845

Data Index: 6039357 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 1.4962. Min Range: -1.4962

Max Act: 1.4642. Min Act: -0.0779

Data Index: 8118300 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 1.4962. Min Range: -1.4962

Max Act: 1.4642. Min Act: -0.1027

Data Index: 7991751 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 1.4962. Min Range: -1.4962

Max Act: 1.4642. Min Act: -0.0802

Data Index: 2694280 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 1.4962. Min Range: -1.4962

Max Act: 1.4504. Min Act: -0.0637

Data Index: 2428306 (Open Web Text)

Max Activating Token Index: 8

Text #9

Max Range: 1.4962. Min Range: -1.4962

Max Act: 1.4412. Min Act: -0.0821

Data Index: 5591572 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 1.4962. Min Range: -1.4962

Max Act: 1.4337. Min Act: -0.1096

Data Index: 666555 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 1.4962. Min Range: -1.4962

Max Act: 1.4160. Min Act: -0.1131

Data Index: 1120970 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 1.4962. Min Range: -1.4962

Max Act: 1.4109. Min Act: -0.0947

Data Index: 157921 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 1.4962. Min Range: -1.4962

Max Act: 1.4129. Min Act: -0.0491

Data Index: 2442269 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 1.4962. Min Range: -1.4962

Max Act: 1.4027. Min Act: -0.0482

Data Index: 2387575 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 1.4962. Min Range: -1.4962

Max Act: 1.4019. Min Act: -0.0987

Data Index: 910129 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 1.4962. Min Range: -1.4962

Max Act: 1.4027. Min Act: -0.0482

Data Index: 3648400 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 1.4962. Min Range: -1.4962

Max Act: 1.3923. Min Act: -0.1247

Data Index: 2558295 (Open Web Text)

Max Activating Token Index: 9

Text #18

Max Range: 1.4962. Min Range: -1.4962

Max Act: 1.3871. Min Act: -0.0655

Data Index: 516953 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 1.4962. Min Range: -1.4962

Max Act: 1.3804. Min Act: -0.0948

Data Index: 79947 (Open Web Text)

Max Activating Token Index: 8