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

Dataset: Open Web Text

Neuron 208 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: 3.0221. Min Range: -3.0221

Max Act: 3.0221. Min Act: -0.1700

Data Index: 4161563 (Open Web Text)

Max Activating Token Index: 584

Text #1

Max Range: 3.0221. Min Range: -3.0221

Max Act: 3.0046. Min Act: -0.1700

Data Index: 1748394 (Open Web Text)

Max Activating Token Index: 258

Text #2

Max Range: 3.0221. Min Range: -3.0221

Max Act: 2.9393. Min Act: -0.1700

Data Index: 5806075 (Open Web Text)

Max Activating Token Index: 373

Text #3

Max Range: 3.0221. Min Range: -3.0221

Max Act: 2.8743. Min Act: -0.1700

Data Index: 3975292 (Open Web Text)

Max Activating Token Index: 602

Text #4

Max Range: 3.0221. Min Range: -3.0221

Max Act: 2.9049. Min Act: -0.1700

Data Index: 4371482 (Open Web Text)

Max Activating Token Index: 991

Text #5

Max Range: 3.0221. Min Range: -3.0221

Max Act: 2.8447. Min Act: -0.1700

Data Index: 4102065 (Open Web Text)

Max Activating Token Index: 936

Text #6

Max Range: 3.0221. Min Range: -3.0221

Max Act: 2.8436. Min Act: -0.1700

Data Index: 2399033 (Open Web Text)

Max Activating Token Index: 43

Text #7

Max Range: 3.0221. Min Range: -3.0221

Max Act: 2.8465. Min Act: -0.1700

Data Index: 5987872 (Open Web Text)

Max Activating Token Index: 694

Text #8

Max Range: 3.0221. Min Range: -3.0221

Max Act: 2.8467. Min Act: -0.1700

Data Index: 5989338 (Open Web Text)

Max Activating Token Index: 930

Text #9

Max Range: 3.0221. Min Range: -3.0221

Max Act: 2.8589. Min Act: -0.1700

Data Index: 3288638 (Open Web Text)

Max Activating Token Index: 634

Text #10

Max Range: 3.0221. Min Range: -3.0221

Max Act: 2.8559. Min Act: -0.1700

Data Index: 3083735 (Open Web Text)

Max Activating Token Index: 988

Text #11

Max Range: 3.0221. Min Range: -3.0221

Max Act: 2.8043. Min Act: -0.1700

Data Index: 7019595 (Open Web Text)

Max Activating Token Index: 986

Text #12

Max Range: 3.0221. Min Range: -3.0221

Max Act: 2.8292. Min Act: -0.1700

Data Index: 7692693 (Open Web Text)

Max Activating Token Index: 385

Text #13

Max Range: 3.0221. Min Range: -3.0221

Max Act: 2.8174. Min Act: -0.1700

Data Index: 2397083 (Open Web Text)

Max Activating Token Index: 455

Text #14

Max Range: 3.0221. Min Range: -3.0221

Max Act: 2.7991. Min Act: -0.1700

Data Index: 66752 (Open Web Text)

Max Activating Token Index: 498

Text #15

Max Range: 3.0221. Min Range: -3.0221

Max Act: 2.8175. Min Act: -0.1700

Data Index: 4041261 (Open Web Text)

Max Activating Token Index: 395

Text #16

Max Range: 3.0221. Min Range: -3.0221

Max Act: 2.8286. Min Act: -0.1700

Data Index: 5467382 (Open Web Text)

Max Activating Token Index: 576

Text #17

Max Range: 3.0221. Min Range: -3.0221

Max Act: 2.8133. Min Act: -0.1700

Data Index: 4818768 (Open Web Text)

Max Activating Token Index: 547

Text #18

Max Range: 3.0221. Min Range: -3.0221

Max Act: 2.8205. Min Act: -0.1700

Data Index: 1028478 (Open Web Text)

Max Activating Token Index: 686

Text #19

Max Range: 3.0221. Min Range: -3.0221

Max Act: 2.8166. Min Act: -0.1700

Data Index: 7411228 (Open Web Text)

Max Activating Token Index: 770