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

Dataset: Open Web Text

Neuron 1764 in Layer 5

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: 2.8793. Min Range: -2.8793

Max Act: 2.8793. Min Act: -0.1700

Data Index: 2378926 (Open Web Text)

Max Activating Token Index: 372

Text #1

Max Range: 2.8793. Min Range: -2.8793

Max Act: 2.8234. Min Act: -0.1700

Data Index: 7264510 (Open Web Text)

Max Activating Token Index: 730

Text #2

Max Range: 2.8793. Min Range: -2.8793

Max Act: 2.8446. Min Act: -0.1700

Data Index: 7570849 (Open Web Text)

Max Activating Token Index: 265

Text #3

Max Range: 2.8793. Min Range: -2.8793

Max Act: 2.8315. Min Act: -0.1700

Data Index: 2196004 (Open Web Text)

Max Activating Token Index: 266

Text #4

Max Range: 2.8793. Min Range: -2.8793

Max Act: 2.8044. Min Act: -0.1700

Data Index: 4982228 (Open Web Text)

Max Activating Token Index: 856

Text #5

Max Range: 2.8793. Min Range: -2.8793

Max Act: 2.8357. Min Act: -0.1700

Data Index: 7393871 (Open Web Text)

Max Activating Token Index: 711

Text #6

Max Range: 2.8793. Min Range: -2.8793

Max Act: 2.8163. Min Act: -0.1700

Data Index: 3701286 (Open Web Text)

Max Activating Token Index: 663

Text #7

Max Range: 2.8793. Min Range: -2.8793

Max Act: 2.7738. Min Act: -0.1700

Data Index: 3797766 (Open Web Text)

Max Activating Token Index: 601

Text #8

Max Range: 2.8793. Min Range: -2.8793

Max Act: 2.7142. Min Act: -0.1700

Data Index: 5019148 (Open Web Text)

Max Activating Token Index: 696

Text #9

Max Range: 2.8793. Min Range: -2.8793

Max Act: 2.7456. Min Act: -0.1700

Data Index: 2819396 (Open Web Text)

Max Activating Token Index: 1022

Text #10

Max Range: 2.8793. Min Range: -2.8793

Max Act: 2.7247. Min Act: -0.1700

Data Index: 5087 (Open Web Text)

Max Activating Token Index: 605

Text #11

Max Range: 2.8793. Min Range: -2.8793

Max Act: 2.7138. Min Act: -0.1700

Data Index: 7238656 (Open Web Text)

Max Activating Token Index: 763

Text #12

Max Range: 2.8793. Min Range: -2.8793

Max Act: 2.6948. Min Act: -0.1700

Data Index: 8696898 (Open Web Text)

Max Activating Token Index: 202

Text #13

Max Range: 2.8793. Min Range: -2.8793

Max Act: 2.7252. Min Act: -0.1700

Data Index: 3757125 (Open Web Text)

Max Activating Token Index: 285

Text #14

Max Range: 2.8793. Min Range: -2.8793

Max Act: 2.7233. Min Act: -0.1700

Data Index: 2143175 (Open Web Text)

Max Activating Token Index: 134

Text #15

Max Range: 2.8793. Min Range: -2.8793

Max Act: 2.6948. Min Act: -0.1700

Data Index: 3322631 (Open Web Text)

Max Activating Token Index: 939

Text #16

Max Range: 2.8793. Min Range: -2.8793

Max Act: 2.7018. Min Act: -0.1700

Data Index: 4450635 (Open Web Text)

Max Activating Token Index: 325

Text #17

Max Range: 2.8793. Min Range: -2.8793

Max Act: 2.6997. Min Act: -0.1700

Data Index: 8696688 (Open Web Text)

Max Activating Token Index: 187

Text #18

Max Range: 2.8793. Min Range: -2.8793

Max Act: 2.6855. Min Act: -0.1700

Data Index: 2198777 (Open Web Text)

Max Activating Token Index: 223

Text #19

Max Range: 2.8793. Min Range: -2.8793

Max Act: 2.7088. Min Act: -0.1700

Data Index: 7835660 (Open Web Text)

Max Activating Token Index: 133