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

Dataset: Open Web Text

Neuron 2430 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: 3.6249. Min Range: -3.6249

Max Act: 3.6249. Min Act: -0.1700

Data Index: 4217653 (Open Web Text)

Max Activating Token Index: 769

Text #1

Max Range: 3.6249. Min Range: -3.6249

Max Act: 3.4948. Min Act: -0.1700

Data Index: 4817143 (Open Web Text)

Max Activating Token Index: 380

Text #2

Max Range: 3.6249. Min Range: -3.6249

Max Act: 3.5021. Min Act: -0.1700

Data Index: 5194549 (Open Web Text)

Max Activating Token Index: 552

Text #3

Max Range: 3.6249. Min Range: -3.6249

Max Act: 3.4662. Min Act: -0.1700

Data Index: 4861112 (Open Web Text)

Max Activating Token Index: 673

Text #4

Max Range: 3.6249. Min Range: -3.6249

Max Act: 3.4430. Min Act: -0.1700

Data Index: 4212097 (Open Web Text)

Max Activating Token Index: 404

Text #5

Max Range: 3.6249. Min Range: -3.6249

Max Act: 3.4431. Min Act: -0.1700

Data Index: 2536818 (Open Web Text)

Max Activating Token Index: 875

Text #6

Max Range: 3.6249. Min Range: -3.6249

Max Act: 3.4368. Min Act: -0.1700

Data Index: 6384983 (Open Web Text)

Max Activating Token Index: 671

Text #7

Max Range: 3.6249. Min Range: -3.6249

Max Act: 3.4175. Min Act: -0.1700

Data Index: 4378668 (Open Web Text)

Max Activating Token Index: 126

Text #8

Max Range: 3.6249. Min Range: -3.6249

Max Act: 3.3389. Min Act: -0.1700

Data Index: 1339628 (Open Web Text)

Max Activating Token Index: 563

Text #9

Max Range: 3.6249. Min Range: -3.6249

Max Act: 3.3046. Min Act: -0.1700

Data Index: 6027717 (Open Web Text)

Max Activating Token Index: 768

Text #10

Max Range: 3.6249. Min Range: -3.6249

Max Act: 3.3207. Min Act: -0.1700

Data Index: 4304853 (Open Web Text)

Max Activating Token Index: 175

Text #11

Max Range: 3.6249. Min Range: -3.6249

Max Act: 3.2998. Min Act: -0.1700

Data Index: 1294825 (Open Web Text)

Max Activating Token Index: 103

Text #12

Max Range: 3.6249. Min Range: -3.6249

Max Act: 3.2701. Min Act: -0.1700

Data Index: 8416214 (Open Web Text)

Max Activating Token Index: 185

Text #13

Max Range: 3.6249. Min Range: -3.6249

Max Act: 3.2454. Min Act: -0.1700

Data Index: 7429029 (Open Web Text)

Max Activating Token Index: 245

Text #14

Max Range: 3.6249. Min Range: -3.6249

Max Act: 3.2755. Min Act: -0.1700

Data Index: 6871599 (Open Web Text)

Max Activating Token Index: 683

Text #15

Max Range: 3.6249. Min Range: -3.6249

Max Act: 3.3475. Min Act: -0.1700

Data Index: 7661954 (Open Web Text)

Max Activating Token Index: 996

Text #16

Max Range: 3.6249. Min Range: -3.6249

Max Act: 3.2565. Min Act: -0.1700

Data Index: 8337381 (Open Web Text)

Max Activating Token Index: 287

Text #17

Max Range: 3.6249. Min Range: -3.6249

Max Act: 3.2211. Min Act: -0.1700

Data Index: 6990947 (Open Web Text)

Max Activating Token Index: 988

Text #18

Max Range: 3.6249. Min Range: -3.6249

Max Act: 3.2327. Min Act: -0.1700

Data Index: 4713397 (Open Web Text)

Max Activating Token Index: 794

Text #19

Max Range: 3.6249. Min Range: -3.6249

Max Act: 3.2280. Min Act: -0.1700

Data Index: 3738296 (Open Web Text)

Max Activating Token Index: 65