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

Dataset: Open Web Text

Neuron 1320 in Layer 3

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: 3.4766. Min Range: -3.4766

Max Act: 3.4766. Min Act: -0.1700

Data Index: 923280 (Open Web Text)

Max Activating Token Index: 698

Text #1

Max Range: 3.4766. Min Range: -3.4766

Max Act: 3.3703. Min Act: -0.1700

Data Index: 1407143 (Open Web Text)

Max Activating Token Index: 646

Text #2

Max Range: 3.4766. Min Range: -3.4766

Max Act: 3.4084. Min Act: -0.1700

Data Index: 4541274 (Open Web Text)

Max Activating Token Index: 709

Text #3

Max Range: 3.4766. Min Range: -3.4766

Max Act: 3.3638. Min Act: -0.1700

Data Index: 1353683 (Open Web Text)

Max Activating Token Index: 985

Text #4

Max Range: 3.4766. Min Range: -3.4766

Max Act: 3.3803. Min Act: -0.1700

Data Index: 3084157 (Open Web Text)

Max Activating Token Index: 310

Text #5

Max Range: 3.4766. Min Range: -3.4766

Max Act: 3.3370. Min Act: -0.1700

Data Index: 6187164 (Open Web Text)

Max Activating Token Index: 117

Text #6

Max Range: 3.4766. Min Range: -3.4766

Max Act: 3.3641. Min Act: -0.1700

Data Index: 593228 (Open Web Text)

Max Activating Token Index: 10

Text #7

Max Range: 3.4766. Min Range: -3.4766

Max Act: 3.3489. Min Act: -0.1700

Data Index: 1478783 (Open Web Text)

Max Activating Token Index: 676

Text #8

Max Range: 3.4766. Min Range: -3.4766

Max Act: 3.3419. Min Act: -0.1700

Data Index: 7720116 (Open Web Text)

Max Activating Token Index: 664

Text #9

Max Range: 3.4766. Min Range: -3.4766

Max Act: 3.2966. Min Act: -0.1700

Data Index: 4646306 (Open Web Text)

Max Activating Token Index: 412

Text #10

Max Range: 3.4766. Min Range: -3.4766

Max Act: 3.3292. Min Act: -0.1700

Data Index: 2428313 (Open Web Text)

Max Activating Token Index: 945

Text #11

Max Range: 3.4766. Min Range: -3.4766

Max Act: 3.3006. Min Act: -0.1700

Data Index: 2186027 (Open Web Text)

Max Activating Token Index: 964

Text #12

Max Range: 3.4766. Min Range: -3.4766

Max Act: 3.3163. Min Act: -0.1700

Data Index: 6517586 (Open Web Text)

Max Activating Token Index: 85

Text #13

Max Range: 3.4766. Min Range: -3.4766

Max Act: 3.3048. Min Act: -0.1700

Data Index: 775180 (Open Web Text)

Max Activating Token Index: 639

Text #14

Max Range: 3.4766. Min Range: -3.4766

Max Act: 3.3086. Min Act: -0.1700

Data Index: 2760436 (Open Web Text)

Max Activating Token Index: 237

Text #15

Max Range: 3.4766. Min Range: -3.4766

Max Act: 3.2855. Min Act: -0.1700

Data Index: 7786356 (Open Web Text)

Max Activating Token Index: 286

Text #16

Max Range: 3.4766. Min Range: -3.4766

Max Act: 3.2954. Min Act: -0.1700

Data Index: 5691630 (Open Web Text)

Max Activating Token Index: 69

Text #17

Max Range: 3.4766. Min Range: -3.4766

Max Act: 3.3113. Min Act: -0.1700

Data Index: 4801848 (Open Web Text)

Max Activating Token Index: 702

Text #18

Max Range: 3.4766. Min Range: -3.4766

Max Act: 3.2897. Min Act: -0.1700

Data Index: 6928376 (Open Web Text)

Max Activating Token Index: 259

Text #19

Max Range: 3.4766. Min Range: -3.4766

Max Act: 3.2916. Min Act: -0.1700

Data Index: 3827542 (Open Web Text)

Max Activating Token Index: 182