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

Dataset: Open Web Text

Neuron 385 in Layer 1

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: 4.3488. Min Range: -4.3488

Max Act: 4.3488. Min Act: -0.1700

Data Index: 8645755 (Open Web Text)

Max Activating Token Index: 235

Text #1

Max Range: 4.3488. Min Range: -4.3488

Max Act: 4.3375. Min Act: -0.1700

Data Index: 6475283 (Open Web Text)

Max Activating Token Index: 553

Text #2

Max Range: 4.3488. Min Range: -4.3488

Max Act: 4.3136. Min Act: -0.1700

Data Index: 1069765 (Open Web Text)

Max Activating Token Index: 208

Text #3

Max Range: 4.3488. Min Range: -4.3488

Max Act: 4.3169. Min Act: -0.1700

Data Index: 3472216 (Open Web Text)

Max Activating Token Index: 718

Text #4

Max Range: 4.3488. Min Range: -4.3488

Max Act: 4.3266. Min Act: -0.1700

Data Index: 5755931 (Open Web Text)

Max Activating Token Index: 694

Text #5

Max Range: 4.3488. Min Range: -4.3488

Max Act: 4.3074. Min Act: -0.1700

Data Index: 2771922 (Open Web Text)

Max Activating Token Index: 111

Text #6

Max Range: 4.3488. Min Range: -4.3488

Max Act: 4.3151. Min Act: -0.1700

Data Index: 5908977 (Open Web Text)

Max Activating Token Index: 202

Text #7

Max Range: 4.3488. Min Range: -4.3488

Max Act: 4.3063. Min Act: -0.1700

Data Index: 4369407 (Open Web Text)

Max Activating Token Index: 356

Text #8

Max Range: 4.3488. Min Range: -4.3488

Max Act: 4.3073. Min Act: -0.1700

Data Index: 726910 (Open Web Text)

Max Activating Token Index: 500

Text #9

Max Range: 4.3488. Min Range: -4.3488

Max Act: 4.3052. Min Act: -0.1700

Data Index: 6150301 (Open Web Text)

Max Activating Token Index: 526

Text #10

Max Range: 4.3488. Min Range: -4.3488

Max Act: 4.2824. Min Act: -0.1700

Data Index: 3835769 (Open Web Text)

Max Activating Token Index: 379

Text #11

Max Range: 4.3488. Min Range: -4.3488

Max Act: 4.2822. Min Act: -0.1700

Data Index: 7717673 (Open Web Text)

Max Activating Token Index: 172

Text #12

Max Range: 4.3488. Min Range: -4.3488

Max Act: 4.2776. Min Act: -0.1700

Data Index: 7661970 (Open Web Text)

Max Activating Token Index: 1003

Text #13

Max Range: 4.3488. Min Range: -4.3488

Max Act: 4.2927. Min Act: -0.1700

Data Index: 6494738 (Open Web Text)

Max Activating Token Index: 230

Text #14

Max Range: 4.3488. Min Range: -4.3488

Max Act: 4.2781. Min Act: -0.1700

Data Index: 3231207 (Open Web Text)

Max Activating Token Index: 180

Text #15

Max Range: 4.3488. Min Range: -4.3488

Max Act: 4.3014. Min Act: -0.1700

Data Index: 5787043 (Open Web Text)

Max Activating Token Index: 890

Text #16

Max Range: 4.3488. Min Range: -4.3488

Max Act: 4.3104. Min Act: -0.1700

Data Index: 4967351 (Open Web Text)

Max Activating Token Index: 658

Text #17

Max Range: 4.3488. Min Range: -4.3488

Max Act: 4.3044. Min Act: -0.1700

Data Index: 2489273 (Open Web Text)

Max Activating Token Index: 692

Text #18

Max Range: 4.3488. Min Range: -4.3488

Max Act: 4.2648. Min Act: -0.1700

Data Index: 4941411 (Open Web Text)

Max Activating Token Index: 728

Text #19

Max Range: 4.3488. Min Range: -4.3488

Max Act: 4.2945. Min Act: -0.1700

Data Index: 2205271 (Open Web Text)

Max Activating Token Index: 647