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

Dataset: Open Web Text

Neuron 1704 in Layer 0

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: 4.5153. Min Range: -4.5153

Max Act: 4.5153. Min Act: -0.1700

Data Index: 2592948 (Open Web Text)

Max Activating Token Index: 43

Text #1

Max Range: 4.5153. Min Range: -4.5153

Max Act: 4.4463. Min Act: -0.1700

Data Index: 2974092 (Open Web Text)

Max Activating Token Index: 67

Text #2

Max Range: 4.5153. Min Range: -4.5153

Max Act: 4.3944. Min Act: -0.1700

Data Index: 6148488 (Open Web Text)

Max Activating Token Index: 41

Text #3

Max Range: 4.5153. Min Range: -4.5153

Max Act: 4.3337. Min Act: -0.1700

Data Index: 4780693 (Open Web Text)

Max Activating Token Index: 295

Text #4

Max Range: 4.5153. Min Range: -4.5153

Max Act: 4.3314. Min Act: -0.1700

Data Index: 5406561 (Open Web Text)

Max Activating Token Index: 69

Text #5

Max Range: 4.5153. Min Range: -4.5153

Max Act: 4.2943. Min Act: -0.1700

Data Index: 2025277 (Open Web Text)

Max Activating Token Index: 285

Text #6

Max Range: 4.5153. Min Range: -4.5153

Max Act: 4.3135. Min Act: -0.1700

Data Index: 3480304 (Open Web Text)

Max Activating Token Index: 55

Text #7

Max Range: 4.5153. Min Range: -4.5153

Max Act: 4.2858. Min Act: -0.1700

Data Index: 3438920 (Open Web Text)

Max Activating Token Index: 150

Text #8

Max Range: 4.5153. Min Range: -4.5153

Max Act: 4.2835. Min Act: -0.1700

Data Index: 6630924 (Open Web Text)

Max Activating Token Index: 82

Text #9

Max Range: 4.5153. Min Range: -4.5153

Max Act: 4.2826. Min Act: -0.1700

Data Index: 2974089 (Open Web Text)

Max Activating Token Index: 325

Text #10

Max Range: 4.5153. Min Range: -4.5153

Max Act: 4.2734. Min Act: -0.1700

Data Index: 1777251 (Open Web Text)

Max Activating Token Index: 412

Text #11

Max Range: 4.5153. Min Range: -4.5153

Max Act: 4.2811. Min Act: -0.1700

Data Index: 5178436 (Open Web Text)

Max Activating Token Index: 24

Text #12

Max Range: 4.5153. Min Range: -4.5153

Max Act: 4.2737. Min Act: -0.1700

Data Index: 1343161 (Open Web Text)

Max Activating Token Index: 287

Text #13

Max Range: 4.5153. Min Range: -4.5153

Max Act: 4.2551. Min Act: -0.1700

Data Index: 2592940 (Open Web Text)

Max Activating Token Index: 102

Text #14

Max Range: 4.5153. Min Range: -4.5153

Max Act: 4.2684. Min Act: -0.1700

Data Index: 3258873 (Open Web Text)

Max Activating Token Index: 48

Text #15

Max Range: 4.5153. Min Range: -4.5153

Max Act: 4.2515. Min Act: -0.1700

Data Index: 7657053 (Open Web Text)

Max Activating Token Index: 94

Text #16

Max Range: 4.5153. Min Range: -4.5153

Max Act: 4.2380. Min Act: -0.1700

Data Index: 4780695 (Open Web Text)

Max Activating Token Index: 24

Text #17

Max Range: 4.5153. Min Range: -4.5153

Max Act: 4.2522. Min Act: -0.1700

Data Index: 4780698 (Open Web Text)

Max Activating Token Index: 87

Text #18

Max Range: 4.5153. Min Range: -4.5153

Max Act: 4.2425. Min Act: -0.1700

Data Index: 4117261 (Open Web Text)

Max Activating Token Index: 478

Text #19

Max Range: 4.5153. Min Range: -4.5153

Max Act: 4.2237. Min Act: -0.1700

Data Index: 3658688 (Open Web Text)

Max Activating Token Index: 248