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

Dataset: Open Web Text

Neuron 2407 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: 4.8987. Min Range: -4.8987

Max Act: 4.8987. Min Act: -0.1700

Data Index: 2078798 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 4.8987. Min Range: -4.8987

Max Act: 4.7867. Min Act: -0.1700

Data Index: 2275870 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 4.8987. Min Range: -4.8987

Max Act: 4.7867. Min Act: -0.1700

Data Index: 5660298 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 4.8987. Min Range: -4.8987

Max Act: 4.7619. Min Act: -0.1700

Data Index: 1484413 (Open Web Text)

Max Activating Token Index: 788

Text #4

Max Range: 4.8987. Min Range: -4.8987

Max Act: 4.7171. Min Act: -0.1700

Data Index: 7267762 (Open Web Text)

Max Activating Token Index: 721

Text #5

Max Range: 4.8987. Min Range: -4.8987

Max Act: 4.6694. Min Act: -0.1700

Data Index: 7135424 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 4.8987. Min Range: -4.8987

Max Act: 4.6451. Min Act: -0.1700

Data Index: 4164655 (Open Web Text)

Max Activating Token Index: 464

Text #7

Max Range: 4.8987. Min Range: -4.8987

Max Act: 4.5785. Min Act: -0.1700

Data Index: 1565811 (Open Web Text)

Max Activating Token Index: 1022

Text #8

Max Range: 4.8987. Min Range: -4.8987

Max Act: 4.5341. Min Act: -0.1700

Data Index: 8482528 (Open Web Text)

Max Activating Token Index: 927

Text #9

Max Range: 4.8987. Min Range: -4.8987

Max Act: 4.5660. Min Act: -0.1700

Data Index: 6329244 (Open Web Text)

Max Activating Token Index: 170

Text #10

Max Range: 4.8987. Min Range: -4.8987

Max Act: 4.5687. Min Act: -0.1700

Data Index: 5328581 (Open Web Text)

Max Activating Token Index: 470

Text #11

Max Range: 4.8987. Min Range: -4.8987

Max Act: 4.5469. Min Act: -0.1700

Data Index: 6441416 (Open Web Text)

Max Activating Token Index: 781

Text #12

Max Range: 4.8987. Min Range: -4.8987

Max Act: 4.5513. Min Act: -0.1700

Data Index: 5894545 (Open Web Text)

Max Activating Token Index: 438

Text #13

Max Range: 4.8987. Min Range: -4.8987

Max Act: 4.5061. Min Act: -0.1700

Data Index: 399749 (Open Web Text)

Max Activating Token Index: 43

Text #14

Max Range: 4.8987. Min Range: -4.8987

Max Act: 4.5440. Min Act: -0.1700

Data Index: 5324536 (Open Web Text)

Max Activating Token Index: 443

Text #15

Max Range: 4.8987. Min Range: -4.8987

Max Act: 4.4866. Min Act: -0.1700

Data Index: 2804352 (Open Web Text)

Max Activating Token Index: 140

Text #16

Max Range: 4.8987. Min Range: -4.8987

Max Act: 4.4881. Min Act: -0.1700

Data Index: 3896353 (Open Web Text)

Max Activating Token Index: 139

Text #17

Max Range: 4.8987. Min Range: -4.8987

Max Act: 4.5236. Min Act: -0.1700

Data Index: 5655364 (Open Web Text)

Max Activating Token Index: 292

Text #18

Max Range: 4.8987. Min Range: -4.8987

Max Act: 4.4901. Min Act: -0.1700

Data Index: 2130625 (Open Web Text)

Max Activating Token Index: 79

Text #19

Max Range: 4.8987. Min Range: -4.8987

Max Act: 4.4444. Min Act: -0.1700

Data Index: 537631 (Open Web Text)

Max Activating Token Index: 478