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

Dataset: Open Web Text

Neuron 2251 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: 5.5961. Min Range: -5.5961

Max Act: 5.5961. Min Act: -0.1700

Data Index: 1672254 (Open Web Text)

Max Activating Token Index: 303

Text #1

Max Range: 5.5961. Min Range: -5.5961

Max Act: 5.4401. Min Act: -0.1700

Data Index: 1365956 (Open Web Text)

Max Activating Token Index: 19

Text #2

Max Range: 5.5961. Min Range: -5.5961

Max Act: 5.4089. Min Act: -0.1700

Data Index: 8199890 (Open Web Text)

Max Activating Token Index: 802

Text #3

Max Range: 5.5961. Min Range: -5.5961

Max Act: 5.4374. Min Act: -0.1700

Data Index: 4606275 (Open Web Text)

Max Activating Token Index: 468

Text #4

Max Range: 5.5961. Min Range: -5.5961

Max Act: 5.4437. Min Act: -0.1700

Data Index: 5620663 (Open Web Text)

Max Activating Token Index: 496

Text #5

Max Range: 5.5961. Min Range: -5.5961

Max Act: 5.3526. Min Act: -0.1700

Data Index: 200285 (Open Web Text)

Max Activating Token Index: 371

Text #6

Max Range: 5.5961. Min Range: -5.5961

Max Act: 5.3783. Min Act: -0.1700

Data Index: 1414834 (Open Web Text)

Max Activating Token Index: 878

Text #7

Max Range: 5.5961. Min Range: -5.5961

Max Act: 5.4979. Min Act: -0.1700

Data Index: 2605587 (Open Web Text)

Max Activating Token Index: 733

Text #8

Max Range: 5.5961. Min Range: -5.5961

Max Act: 5.3920. Min Act: -0.1700

Data Index: 5248016 (Open Web Text)

Max Activating Token Index: 617

Text #9

Max Range: 5.5961. Min Range: -5.5961

Max Act: 5.3457. Min Act: -0.1700

Data Index: 1313354 (Open Web Text)

Max Activating Token Index: 765

Text #10

Max Range: 5.5961. Min Range: -5.5961

Max Act: 5.3149. Min Act: -0.1700

Data Index: 7201316 (Open Web Text)

Max Activating Token Index: 236

Text #11

Max Range: 5.5961. Min Range: -5.5961

Max Act: 5.3330. Min Act: -0.1700

Data Index: 2025164 (Open Web Text)

Max Activating Token Index: 861

Text #12

Max Range: 5.5961. Min Range: -5.5961

Max Act: 5.2993. Min Act: -0.1700

Data Index: 7636110 (Open Web Text)

Max Activating Token Index: 65

Text #13

Max Range: 5.5961. Min Range: -5.5961

Max Act: 5.2995. Min Act: -0.1700

Data Index: 6021174 (Open Web Text)

Max Activating Token Index: 419

Text #14

Max Range: 5.5961. Min Range: -5.5961

Max Act: 5.3265. Min Act: -0.1700

Data Index: 2837669 (Open Web Text)

Max Activating Token Index: 412

Text #15

Max Range: 5.5961. Min Range: -5.5961

Max Act: 5.3168. Min Act: -0.1700

Data Index: 3821152 (Open Web Text)

Max Activating Token Index: 244

Text #16

Max Range: 5.5961. Min Range: -5.5961

Max Act: 5.3095. Min Act: -0.1700

Data Index: 576199 (Open Web Text)

Max Activating Token Index: 490

Text #17

Max Range: 5.5961. Min Range: -5.5961

Max Act: 5.3623. Min Act: -0.1700

Data Index: 3717877 (Open Web Text)

Max Activating Token Index: 830

Text #18

Max Range: 5.5961. Min Range: -5.5961

Max Act: 5.3260. Min Act: -0.1700

Data Index: 7152716 (Open Web Text)

Max Activating Token Index: 424

Text #19

Max Range: 5.5961. Min Range: -5.5961

Max Act: 5.3279. Min Act: -0.1700

Data Index: 6868631 (Open Web Text)

Max Activating Token Index: 454