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

Dataset: Open Web Text

Neuron 89 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: 3.2335. Min Range: -3.2335

Max Act: 3.2335. Min Act: -0.1700

Data Index: 1758649 (Open Web Text)

Max Activating Token Index: 46

Text #1

Max Range: 3.2335. Min Range: -3.2335

Max Act: 3.1377. Min Act: -0.1700

Data Index: 5355979 (Open Web Text)

Max Activating Token Index: 580

Text #2

Max Range: 3.2335. Min Range: -3.2335

Max Act: 3.0913. Min Act: -0.1700

Data Index: 6008832 (Open Web Text)

Max Activating Token Index: 401

Text #3

Max Range: 3.2335. Min Range: -3.2335

Max Act: 3.0670. Min Act: -0.1700

Data Index: 3554683 (Open Web Text)

Max Activating Token Index: 667

Text #4

Max Range: 3.2335. Min Range: -3.2335

Max Act: 3.0578. Min Act: -0.1700

Data Index: 4406572 (Open Web Text)

Max Activating Token Index: 249

Text #5

Max Range: 3.2335. Min Range: -3.2335

Max Act: 3.0136. Min Act: -0.1700

Data Index: 8572843 (Open Web Text)

Max Activating Token Index: 586

Text #6

Max Range: 3.2335. Min Range: -3.2335

Max Act: 3.0046. Min Act: -0.1700

Data Index: 3467708 (Open Web Text)

Max Activating Token Index: 192

Text #7

Max Range: 3.2335. Min Range: -3.2335

Max Act: 3.0114. Min Act: -0.1700

Data Index: 7292949 (Open Web Text)

Max Activating Token Index: 178

Text #8

Max Range: 3.2335. Min Range: -3.2335

Max Act: 3.0155. Min Act: -0.1700

Data Index: 3170360 (Open Web Text)

Max Activating Token Index: 592

Text #9

Max Range: 3.2335. Min Range: -3.2335

Max Act: 2.9810. Min Act: -0.1700

Data Index: 5433552 (Open Web Text)

Max Activating Token Index: 129

Text #10

Max Range: 3.2335. Min Range: -3.2335

Max Act: 2.9842. Min Act: -0.1700

Data Index: 952286 (Open Web Text)

Max Activating Token Index: 194

Text #11

Max Range: 3.2335. Min Range: -3.2335

Max Act: 3.0072. Min Act: -0.1700

Data Index: 4620580 (Open Web Text)

Max Activating Token Index: 132

Text #12

Max Range: 3.2335. Min Range: -3.2335

Max Act: 3.0003. Min Act: -0.1700

Data Index: 1961068 (Open Web Text)

Max Activating Token Index: 133

Text #13

Max Range: 3.2335. Min Range: -3.2335

Max Act: 2.9957. Min Act: -0.1700

Data Index: 669044 (Open Web Text)

Max Activating Token Index: 410

Text #14

Max Range: 3.2335. Min Range: -3.2335

Max Act: 3.0054. Min Act: -0.1700

Data Index: 4158968 (Open Web Text)

Max Activating Token Index: 971

Text #15

Max Range: 3.2335. Min Range: -3.2335

Max Act: 2.9865. Min Act: -0.1700

Data Index: 7210278 (Open Web Text)

Max Activating Token Index: 944

Text #16

Max Range: 3.2335. Min Range: -3.2335

Max Act: 2.9695. Min Act: -0.1700

Data Index: 3289404 (Open Web Text)

Max Activating Token Index: 531

Text #17

Max Range: 3.2335. Min Range: -3.2335

Max Act: 2.9825. Min Act: -0.1700

Data Index: 2414926 (Open Web Text)

Max Activating Token Index: 237

Text #18

Max Range: 3.2335. Min Range: -3.2335

Max Act: 2.9681. Min Act: -0.1700

Data Index: 2723044 (Open Web Text)

Max Activating Token Index: 170

Text #19

Max Range: 3.2335. Min Range: -3.2335

Max Act: 2.9777. Min Act: -0.1700

Data Index: 262186 (Open Web Text)

Max Activating Token Index: 435