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

Dataset: Open Web Text

Neuron 957 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: 2.5145. Min Range: -2.5145

Max Act: 2.5145. Min Act: -0.1700

Data Index: 4998129 (Open Web Text)

Max Activating Token Index: 364

Text #1

Max Range: 2.5145. Min Range: -2.5145

Max Act: 2.4097. Min Act: -0.1700

Data Index: 4020441 (Open Web Text)

Max Activating Token Index: 98

Text #2

Max Range: 2.5145. Min Range: -2.5145

Max Act: 2.4236. Min Act: -0.1700

Data Index: 395677 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 2.5145. Min Range: -2.5145

Max Act: 2.4236. Min Act: -0.1700

Data Index: 313282 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 2.5145. Min Range: -2.5145

Max Act: 2.4121. Min Act: -0.1700

Data Index: 8802418 (Open Web Text)

Max Activating Token Index: 59

Text #5

Max Range: 2.5145. Min Range: -2.5145

Max Act: 2.3902. Min Act: -0.1700

Data Index: 3913257 (Open Web Text)

Max Activating Token Index: 759

Text #6

Max Range: 2.5145. Min Range: -2.5145

Max Act: 2.3885. Min Act: -0.1700

Data Index: 8480626 (Open Web Text)

Max Activating Token Index: 169

Text #7

Max Range: 2.5145. Min Range: -2.5145

Max Act: 2.3578. Min Act: -0.1700

Data Index: 7539140 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 2.5145. Min Range: -2.5145

Max Act: 2.3624. Min Act: -0.1700

Data Index: 8097101 (Open Web Text)

Max Activating Token Index: 753

Text #9

Max Range: 2.5145. Min Range: -2.5145

Max Act: 2.2977. Min Act: -0.1700

Data Index: 4811186 (Open Web Text)

Max Activating Token Index: 732

Text #10

Max Range: 2.5145. Min Range: -2.5145

Max Act: 2.3408. Min Act: -0.1700

Data Index: 2399594 (Open Web Text)

Max Activating Token Index: 10

Text #11

Max Range: 2.5145. Min Range: -2.5145

Max Act: 2.3298. Min Act: -0.1700

Data Index: 6865950 (Open Web Text)

Max Activating Token Index: 238

Text #12

Max Range: 2.5145. Min Range: -2.5145

Max Act: 2.3152. Min Act: -0.1700

Data Index: 1868828 (Open Web Text)

Max Activating Token Index: 898

Text #13

Max Range: 2.5145. Min Range: -2.5145

Max Act: 2.3358. Min Act: -0.1700

Data Index: 1340616 (Open Web Text)

Max Activating Token Index: 11

Text #14

Max Range: 2.5145. Min Range: -2.5145

Max Act: 2.3184. Min Act: -0.1700

Data Index: 4348263 (Open Web Text)

Max Activating Token Index: 866

Text #15

Max Range: 2.5145. Min Range: -2.5145

Max Act: 2.3071. Min Act: -0.1700

Data Index: 4388593 (Open Web Text)

Max Activating Token Index: 869

Text #16

Max Range: 2.5145. Min Range: -2.5145

Max Act: 2.3022. Min Act: -0.1700

Data Index: 8784689 (Open Web Text)

Max Activating Token Index: 563

Text #17

Max Range: 2.5145. Min Range: -2.5145

Max Act: 2.2978. Min Act: -0.1700

Data Index: 1489696 (Open Web Text)

Max Activating Token Index: 508

Text #18

Max Range: 2.5145. Min Range: -2.5145

Max Act: 2.2831. Min Act: -0.1700

Data Index: 727770 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 2.5145. Min Range: -2.5145

Max Act: 2.2832. Min Act: -0.1700

Data Index: 4388594 (Open Web Text)

Max Activating Token Index: 59