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

Dataset: Open Web Text

Neuron 387 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: 3.7706. Min Range: -3.7706

Max Act: 3.7706. Min Act: -0.1700

Data Index: 8715129 (Open Web Text)

Max Activating Token Index: 955

Text #1

Max Range: 3.7706. Min Range: -3.7706

Max Act: 3.4619. Min Act: -0.1700

Data Index: 5768529 (Open Web Text)

Max Activating Token Index: 485

Text #2

Max Range: 3.7706. Min Range: -3.7706

Max Act: 3.4035. Min Act: -0.1700

Data Index: 1376561 (Open Web Text)

Max Activating Token Index: 473

Text #3

Max Range: 3.7706. Min Range: -3.7706

Max Act: 3.3909. Min Act: -0.1700

Data Index: 4380013 (Open Web Text)

Max Activating Token Index: 451

Text #4

Max Range: 3.7706. Min Range: -3.7706

Max Act: 3.3568. Min Act: -0.1700

Data Index: 1924609 (Open Web Text)

Max Activating Token Index: 481

Text #5

Max Range: 3.7706. Min Range: -3.7706

Max Act: 3.3724. Min Act: -0.1700

Data Index: 4154235 (Open Web Text)

Max Activating Token Index: 352

Text #6

Max Range: 3.7706. Min Range: -3.7706

Max Act: 3.3289. Min Act: -0.1700

Data Index: 6427483 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 3.7706. Min Range: -3.7706

Max Act: 3.3140. Min Act: -0.1700

Data Index: 4860193 (Open Web Text)

Max Activating Token Index: 404

Text #8

Max Range: 3.7706. Min Range: -3.7706

Max Act: 3.3141. Min Act: -0.1700

Data Index: 2895462 (Open Web Text)

Max Activating Token Index: 169

Text #9

Max Range: 3.7706. Min Range: -3.7706

Max Act: 3.2882. Min Act: -0.1700

Data Index: 8745772 (Open Web Text)

Max Activating Token Index: 747

Text #10

Max Range: 3.7706. Min Range: -3.7706

Max Act: 3.3325. Min Act: -0.1700

Data Index: 2462036 (Open Web Text)

Max Activating Token Index: 382

Text #11

Max Range: 3.7706. Min Range: -3.7706

Max Act: 3.3139. Min Act: -0.1700

Data Index: 8346430 (Open Web Text)

Max Activating Token Index: 770

Text #12

Max Range: 3.7706. Min Range: -3.7706

Max Act: 3.3037. Min Act: -0.1700

Data Index: 1023044 (Open Web Text)

Max Activating Token Index: 469

Text #13

Max Range: 3.7706. Min Range: -3.7706

Max Act: 3.2957. Min Act: -0.1700

Data Index: 6127095 (Open Web Text)

Max Activating Token Index: 397

Text #14

Max Range: 3.7706. Min Range: -3.7706

Max Act: 3.2903. Min Act: -0.1700

Data Index: 1423769 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 3.7706. Min Range: -3.7706

Max Act: 3.2914. Min Act: -0.1700

Data Index: 3250171 (Open Web Text)

Max Activating Token Index: 460

Text #16

Max Range: 3.7706. Min Range: -3.7706

Max Act: 3.2980. Min Act: -0.1700

Data Index: 6289437 (Open Web Text)

Max Activating Token Index: 65

Text #17

Max Range: 3.7706. Min Range: -3.7706

Max Act: 3.2960. Min Act: -0.1700

Data Index: 5749719 (Open Web Text)

Max Activating Token Index: 440

Text #18

Max Range: 3.7706. Min Range: -3.7706

Max Act: 3.2818. Min Act: -0.1700

Data Index: 6651276 (Open Web Text)

Max Activating Token Index: 368

Text #19

Max Range: 3.7706. Min Range: -3.7706

Max Act: 3.2790. Min Act: -0.1700

Data Index: 932193 (Open Web Text)

Max Activating Token Index: 545