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

Dataset: Open Web Text

Neuron 3048 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: 3.4316. Min Range: -3.4316

Max Act: 3.4316. Min Act: -0.1700

Data Index: 3813897 (Open Web Text)

Max Activating Token Index: 899

Text #1

Max Range: 3.4316. Min Range: -3.4316

Max Act: 3.3325. Min Act: -0.1700

Data Index: 4769329 (Open Web Text)

Max Activating Token Index: 132

Text #2

Max Range: 3.4316. Min Range: -3.4316

Max Act: 3.3288. Min Act: -0.1700

Data Index: 7196362 (Open Web Text)

Max Activating Token Index: 730

Text #3

Max Range: 3.4316. Min Range: -3.4316

Max Act: 3.2941. Min Act: -0.1700

Data Index: 2690344 (Open Web Text)

Max Activating Token Index: 396

Text #4

Max Range: 3.4316. Min Range: -3.4316

Max Act: 3.3158. Min Act: -0.1700

Data Index: 5083418 (Open Web Text)

Max Activating Token Index: 323

Text #5

Max Range: 3.4316. Min Range: -3.4316

Max Act: 3.3118. Min Act: -0.1700

Data Index: 6958195 (Open Web Text)

Max Activating Token Index: 158

Text #6

Max Range: 3.4316. Min Range: -3.4316

Max Act: 3.3181. Min Act: -0.1700

Data Index: 1595253 (Open Web Text)

Max Activating Token Index: 256

Text #7

Max Range: 3.4316. Min Range: -3.4316

Max Act: 3.2959. Min Act: -0.1700

Data Index: 6450549 (Open Web Text)

Max Activating Token Index: 257

Text #8

Max Range: 3.4316. Min Range: -3.4316

Max Act: 3.2915. Min Act: -0.1700

Data Index: 5926486 (Open Web Text)

Max Activating Token Index: 116

Text #9

Max Range: 3.4316. Min Range: -3.4316

Max Act: 3.2891. Min Act: -0.1700

Data Index: 7761124 (Open Web Text)

Max Activating Token Index: 818

Text #10

Max Range: 3.4316. Min Range: -3.4316

Max Act: 3.2697. Min Act: -0.1700

Data Index: 5103709 (Open Web Text)

Max Activating Token Index: 746

Text #11

Max Range: 3.4316. Min Range: -3.4316

Max Act: 3.2811. Min Act: -0.1700

Data Index: 588713 (Open Web Text)

Max Activating Token Index: 845

Text #12

Max Range: 3.4316. Min Range: -3.4316

Max Act: 3.2685. Min Act: -0.1700

Data Index: 2428058 (Open Web Text)

Max Activating Token Index: 670

Text #13

Max Range: 3.4316. Min Range: -3.4316

Max Act: 3.2565. Min Act: -0.1700

Data Index: 7468577 (Open Web Text)

Max Activating Token Index: 278

Text #14

Max Range: 3.4316. Min Range: -3.4316

Max Act: 3.2583. Min Act: -0.1700

Data Index: 6000129 (Open Web Text)

Max Activating Token Index: 277

Text #15

Max Range: 3.4316. Min Range: -3.4316

Max Act: 3.2619. Min Act: -0.1700

Data Index: 807626 (Open Web Text)

Max Activating Token Index: 197

Text #16

Max Range: 3.4316. Min Range: -3.4316

Max Act: 3.2589. Min Act: -0.1700

Data Index: 4044191 (Open Web Text)

Max Activating Token Index: 494

Text #17

Max Range: 3.4316. Min Range: -3.4316

Max Act: 3.2540. Min Act: -0.1700

Data Index: 4716178 (Open Web Text)

Max Activating Token Index: 367

Text #18

Max Range: 3.4316. Min Range: -3.4316

Max Act: 3.2530. Min Act: -0.1700

Data Index: 6659078 (Open Web Text)

Max Activating Token Index: 282

Text #19

Max Range: 3.4316. Min Range: -3.4316

Max Act: 3.2516. Min Act: -0.1700

Data Index: 2437210 (Open Web Text)

Max Activating Token Index: 757