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

Dataset: Open Web Text

Neuron 30 in Layer 6

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: 3.7467. Min Range: -3.7467

Max Act: 3.7467. Min Act: -0.1700

Data Index: 1894744 (Open Web Text)

Max Activating Token Index: 288

Text #1

Max Range: 3.7467. Min Range: -3.7467

Max Act: 3.7066. Min Act: -0.1700

Data Index: 2008067 (Open Web Text)

Max Activating Token Index: 219

Text #2

Max Range: 3.7467. Min Range: -3.7467

Max Act: 3.6785. Min Act: -0.1700

Data Index: 8208995 (Open Web Text)

Max Activating Token Index: 957

Text #3

Max Range: 3.7467. Min Range: -3.7467

Max Act: 3.6578. Min Act: -0.1700

Data Index: 2237654 (Open Web Text)

Max Activating Token Index: 260

Text #4

Max Range: 3.7467. Min Range: -3.7467

Max Act: 3.6160. Min Act: -0.1700

Data Index: 8290015 (Open Web Text)

Max Activating Token Index: 435

Text #5

Max Range: 3.7467. Min Range: -3.7467

Max Act: 3.6071. Min Act: -0.1700

Data Index: 3675027 (Open Web Text)

Max Activating Token Index: 332

Text #6

Max Range: 3.7467. Min Range: -3.7467

Max Act: 3.5960. Min Act: -0.1700

Data Index: 1779273 (Open Web Text)

Max Activating Token Index: 752

Text #7

Max Range: 3.7467. Min Range: -3.7467

Max Act: 3.5654. Min Act: -0.1700

Data Index: 44526 (Open Web Text)

Max Activating Token Index: 255

Text #8

Max Range: 3.7467. Min Range: -3.7467

Max Act: 3.5634. Min Act: -0.1700

Data Index: 2881816 (Open Web Text)

Max Activating Token Index: 476

Text #9

Max Range: 3.7467. Min Range: -3.7467

Max Act: 3.5333. Min Act: -0.1700

Data Index: 2461120 (Open Web Text)

Max Activating Token Index: 286

Text #10

Max Range: 3.7467. Min Range: -3.7467

Max Act: 3.5109. Min Act: -0.1700

Data Index: 3885716 (Open Web Text)

Max Activating Token Index: 318

Text #11

Max Range: 3.7467. Min Range: -3.7467

Max Act: 3.4939. Min Act: -0.1700

Data Index: 3208582 (Open Web Text)

Max Activating Token Index: 457

Text #12

Max Range: 3.7467. Min Range: -3.7467

Max Act: 3.5138. Min Act: -0.1700

Data Index: 8813219 (Open Web Text)

Max Activating Token Index: 178

Text #13

Max Range: 3.7467. Min Range: -3.7467

Max Act: 3.4618. Min Act: -0.1700

Data Index: 4794666 (Open Web Text)

Max Activating Token Index: 718

Text #14

Max Range: 3.7467. Min Range: -3.7467

Max Act: 3.4795. Min Act: -0.1700

Data Index: 4649921 (Open Web Text)

Max Activating Token Index: 387

Text #15

Max Range: 3.7467. Min Range: -3.7467

Max Act: 3.4512. Min Act: -0.1700

Data Index: 2733980 (Open Web Text)

Max Activating Token Index: 930

Text #16

Max Range: 3.7467. Min Range: -3.7467

Max Act: 3.4589. Min Act: -0.1700

Data Index: 3261709 (Open Web Text)

Max Activating Token Index: 296

Text #17

Max Range: 3.7467. Min Range: -3.7467

Max Act: 3.4659. Min Act: -0.1700

Data Index: 137090 (Open Web Text)

Max Activating Token Index: 667

Text #18

Max Range: 3.7467. Min Range: -3.7467

Max Act: 3.4649. Min Act: -0.1700

Data Index: 4316054 (Open Web Text)

Max Activating Token Index: 287

Text #19

Max Range: 3.7467. Min Range: -3.7467

Max Act: 3.4458. Min Act: -0.1700

Data Index: 6175160 (Open Web Text)

Max Activating Token Index: 343