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

Dataset: Open Web Text

Neuron 1958 in Layer 4

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: 3.5232. Min Range: -3.5232

Max Act: 3.5232. Min Act: -0.1700

Data Index: 7766426 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.5232. Min Range: -3.5232

Max Act: 3.4872. Min Act: -0.1700

Data Index: 4223221 (Open Web Text)

Max Activating Token Index: 460

Text #2

Max Range: 3.5232. Min Range: -3.5232

Max Act: 3.5084. Min Act: -0.1700

Data Index: 8345094 (Open Web Text)

Max Activating Token Index: 749

Text #3

Max Range: 3.5232. Min Range: -3.5232

Max Act: 3.4902. Min Act: -0.1700

Data Index: 5042524 (Open Web Text)

Max Activating Token Index: 990

Text #4

Max Range: 3.5232. Min Range: -3.5232

Max Act: 3.4217. Min Act: -0.1700

Data Index: 208010 (Open Web Text)

Max Activating Token Index: 371

Text #5

Max Range: 3.5232. Min Range: -3.5232

Max Act: 3.4137. Min Act: -0.1700

Data Index: 2789264 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 3.5232. Min Range: -3.5232

Max Act: 3.4137. Min Act: -0.1700

Data Index: 7209314 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 3.5232. Min Range: -3.5232

Max Act: 3.4137. Min Act: -0.1700

Data Index: 7083115 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 3.5232. Min Range: -3.5232

Max Act: 3.4305. Min Act: -0.1700

Data Index: 1115618 (Open Web Text)

Max Activating Token Index: 947

Text #9

Max Range: 3.5232. Min Range: -3.5232

Max Act: 3.4069. Min Act: -0.1700

Data Index: 5429691 (Open Web Text)

Max Activating Token Index: 580

Text #10

Max Range: 3.5232. Min Range: -3.5232

Max Act: 3.4364. Min Act: -0.1700

Data Index: 969544 (Open Web Text)

Max Activating Token Index: 632

Text #11

Max Range: 3.5232. Min Range: -3.5232

Max Act: 3.4290. Min Act: -0.1700

Data Index: 6919893 (Open Web Text)

Max Activating Token Index: 42

Text #12

Max Range: 3.5232. Min Range: -3.5232

Max Act: 3.3766. Min Act: -0.1700

Data Index: 5520355 (Open Web Text)

Max Activating Token Index: 560

Text #13

Max Range: 3.5232. Min Range: -3.5232

Max Act: 3.3887. Min Act: -0.1700

Data Index: 5475269 (Open Web Text)

Max Activating Token Index: 598

Text #14

Max Range: 3.5232. Min Range: -3.5232

Max Act: 3.3823. Min Act: -0.1700

Data Index: 8505938 (Open Web Text)

Max Activating Token Index: 237

Text #15

Max Range: 3.5232. Min Range: -3.5232

Max Act: 3.3643. Min Act: -0.1700

Data Index: 3356094 (Open Web Text)

Max Activating Token Index: 446

Text #16

Max Range: 3.5232. Min Range: -3.5232

Max Act: 3.3673. Min Act: -0.1700

Data Index: 7238997 (Open Web Text)

Max Activating Token Index: 104

Text #17

Max Range: 3.5232. Min Range: -3.5232

Max Act: 3.3745. Min Act: -0.1700

Data Index: 4903340 (Open Web Text)

Max Activating Token Index: 906

Text #18

Max Range: 3.5232. Min Range: -3.5232

Max Act: 3.3596. Min Act: -0.1700

Data Index: 4532340 (Open Web Text)

Max Activating Token Index: 10

Text #19

Max Range: 3.5232. Min Range: -3.5232

Max Act: 3.3630. Min Act: -0.1700

Data Index: 7307334 (Open Web Text)

Max Activating Token Index: 4