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

Dataset: Open Web Text

Neuron 3000 in Layer 3

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: 3.0330. Min Range: -3.0330

Max Act: 3.0330. Min Act: -0.1700

Data Index: 7814848 (Open Web Text)

Max Activating Token Index: 714

Text #1

Max Range: 3.0330. Min Range: -3.0330

Max Act: 2.9747. Min Act: -0.1700

Data Index: 1477508 (Open Web Text)

Max Activating Token Index: 93

Text #2

Max Range: 3.0330. Min Range: -3.0330

Max Act: 2.9476. Min Act: -0.1700

Data Index: 933680 (Open Web Text)

Max Activating Token Index: 654

Text #3

Max Range: 3.0330. Min Range: -3.0330

Max Act: 2.9541. Min Act: -0.1700

Data Index: 4755116 (Open Web Text)

Max Activating Token Index: 314

Text #4

Max Range: 3.0330. Min Range: -3.0330

Max Act: 2.9431. Min Act: -0.1700

Data Index: 2977067 (Open Web Text)

Max Activating Token Index: 409

Text #5

Max Range: 3.0330. Min Range: -3.0330

Max Act: 2.9137. Min Act: -0.1700

Data Index: 8007731 (Open Web Text)

Max Activating Token Index: 713

Text #6

Max Range: 3.0330. Min Range: -3.0330

Max Act: 2.8565. Min Act: -0.1700

Data Index: 533343 (Open Web Text)

Max Activating Token Index: 602

Text #7

Max Range: 3.0330. Min Range: -3.0330

Max Act: 2.8867. Min Act: -0.1700

Data Index: 624475 (Open Web Text)

Max Activating Token Index: 404

Text #8

Max Range: 3.0330. Min Range: -3.0330

Max Act: 2.8950. Min Act: -0.1700

Data Index: 2091557 (Open Web Text)

Max Activating Token Index: 232

Text #9

Max Range: 3.0330. Min Range: -3.0330

Max Act: 2.8532. Min Act: -0.1700

Data Index: 4114385 (Open Web Text)

Max Activating Token Index: 878

Text #10

Max Range: 3.0330. Min Range: -3.0330

Max Act: 2.8935. Min Act: -0.1700

Data Index: 2967781 (Open Web Text)

Max Activating Token Index: 124

Text #11

Max Range: 3.0330. Min Range: -3.0330

Max Act: 2.8618. Min Act: -0.1700

Data Index: 1819993 (Open Web Text)

Max Activating Token Index: 375

Text #12

Max Range: 3.0330. Min Range: -3.0330

Max Act: 2.8532. Min Act: -0.1700

Data Index: 5883227 (Open Web Text)

Max Activating Token Index: 207

Text #13

Max Range: 3.0330. Min Range: -3.0330

Max Act: 2.8496. Min Act: -0.1700

Data Index: 662 (Open Web Text)

Max Activating Token Index: 194

Text #14

Max Range: 3.0330. Min Range: -3.0330

Max Act: 2.8543. Min Act: -0.1700

Data Index: 5188656 (Open Web Text)

Max Activating Token Index: 548

Text #15

Max Range: 3.0330. Min Range: -3.0330

Max Act: 2.8755. Min Act: -0.1700

Data Index: 8076514 (Open Web Text)

Max Activating Token Index: 576

Text #16

Max Range: 3.0330. Min Range: -3.0330

Max Act: 2.8598. Min Act: -0.1700

Data Index: 3512421 (Open Web Text)

Max Activating Token Index: 89

Text #17

Max Range: 3.0330. Min Range: -3.0330

Max Act: 2.8323. Min Act: -0.1700

Data Index: 5055805 (Open Web Text)

Max Activating Token Index: 942

Text #18

Max Range: 3.0330. Min Range: -3.0330

Max Act: 2.8326. Min Act: -0.1700

Data Index: 7247401 (Open Web Text)

Max Activating Token Index: 32

Text #19

Max Range: 3.0330. Min Range: -3.0330

Max Act: 2.8329. Min Act: -0.1700

Data Index: 7274253 (Open Web Text)

Max Activating Token Index: 941