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

Dataset: Open Web Text

Neuron 1680 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: 4.6103. Min Range: -4.6103

Max Act: 4.6103. Min Act: -0.1700

Data Index: 4017152 (Open Web Text)

Max Activating Token Index: 675

Text #1

Max Range: 4.6103. Min Range: -4.6103

Max Act: 4.5653. Min Act: -0.1700

Data Index: 3552345 (Open Web Text)

Max Activating Token Index: 508

Text #2

Max Range: 4.6103. Min Range: -4.6103

Max Act: 4.5107. Min Act: -0.1700

Data Index: 2474104 (Open Web Text)

Max Activating Token Index: 276

Text #3

Max Range: 4.6103. Min Range: -4.6103

Max Act: 4.5242. Min Act: -0.1700

Data Index: 8390353 (Open Web Text)

Max Activating Token Index: 440

Text #4

Max Range: 4.6103. Min Range: -4.6103

Max Act: 4.4940. Min Act: -0.1700

Data Index: 2049577 (Open Web Text)

Max Activating Token Index: 511

Text #5

Max Range: 4.6103. Min Range: -4.6103

Max Act: 4.5037. Min Act: -0.1700

Data Index: 3057100 (Open Web Text)

Max Activating Token Index: 683

Text #6

Max Range: 4.6103. Min Range: -4.6103

Max Act: 4.4714. Min Act: -0.1700

Data Index: 7209550 (Open Web Text)

Max Activating Token Index: 185

Text #7

Max Range: 4.6103. Min Range: -4.6103

Max Act: 4.4731. Min Act: -0.1700

Data Index: 6514037 (Open Web Text)

Max Activating Token Index: 172

Text #8

Max Range: 4.6103. Min Range: -4.6103

Max Act: 4.4717. Min Act: -0.1700

Data Index: 3971300 (Open Web Text)

Max Activating Token Index: 147

Text #9

Max Range: 4.6103. Min Range: -4.6103

Max Act: 4.4821. Min Act: -0.1700

Data Index: 6505173 (Open Web Text)

Max Activating Token Index: 217

Text #10

Max Range: 4.6103. Min Range: -4.6103

Max Act: 4.4604. Min Act: -0.1700

Data Index: 2798102 (Open Web Text)

Max Activating Token Index: 232

Text #11

Max Range: 4.6103. Min Range: -4.6103

Max Act: 4.4991. Min Act: -0.1700

Data Index: 7868731 (Open Web Text)

Max Activating Token Index: 604

Text #12

Max Range: 4.6103. Min Range: -4.6103

Max Act: 4.4391. Min Act: -0.1700

Data Index: 844530 (Open Web Text)

Max Activating Token Index: 939

Text #13

Max Range: 4.6103. Min Range: -4.6103

Max Act: 4.4298. Min Act: -0.1700

Data Index: 6358125 (Open Web Text)

Max Activating Token Index: 380

Text #14

Max Range: 4.6103. Min Range: -4.6103

Max Act: 4.4494. Min Act: -0.1700

Data Index: 1381883 (Open Web Text)

Max Activating Token Index: 136

Text #15

Max Range: 4.6103. Min Range: -4.6103

Max Act: 4.4100. Min Act: -0.1700

Data Index: 6300315 (Open Web Text)

Max Activating Token Index: 700

Text #16

Max Range: 4.6103. Min Range: -4.6103

Max Act: 4.4338. Min Act: -0.1700

Data Index: 3216018 (Open Web Text)

Max Activating Token Index: 208

Text #17

Max Range: 4.6103. Min Range: -4.6103

Max Act: 4.4297. Min Act: -0.1700

Data Index: 236706 (Open Web Text)

Max Activating Token Index: 206

Text #18

Max Range: 4.6103. Min Range: -4.6103

Max Act: 4.4321. Min Act: -0.1700

Data Index: 6139038 (Open Web Text)

Max Activating Token Index: 213

Text #19

Max Range: 4.6103. Min Range: -4.6103

Max Act: 4.4354. Min Act: -0.1700

Data Index: 2915602 (Open Web Text)

Max Activating Token Index: 83