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

Dataset: Open Web Text

Neuron 601 in Layer 2

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: 4.4020. Min Range: -4.4020

Max Act: 4.4020. Min Act: -0.1700

Data Index: 4986640 (Open Web Text)

Max Activating Token Index: 738

Text #1

Max Range: 4.4020. Min Range: -4.4020

Max Act: 4.3394. Min Act: -0.1700

Data Index: 7232949 (Open Web Text)

Max Activating Token Index: 57

Text #2

Max Range: 4.4020. Min Range: -4.4020

Max Act: 4.3371. Min Act: -0.1700

Data Index: 1225272 (Open Web Text)

Max Activating Token Index: 90

Text #3

Max Range: 4.4020. Min Range: -4.4020

Max Act: 4.2903. Min Act: -0.1700

Data Index: 2488464 (Open Web Text)

Max Activating Token Index: 117

Text #4

Max Range: 4.4020. Min Range: -4.4020

Max Act: 4.2983. Min Act: -0.1700

Data Index: 16777 (Open Web Text)

Max Activating Token Index: 944

Text #5

Max Range: 4.4020. Min Range: -4.4020

Max Act: 4.2988. Min Act: -0.1700

Data Index: 7945214 (Open Web Text)

Max Activating Token Index: 598

Text #6

Max Range: 4.4020. Min Range: -4.4020

Max Act: 4.2869. Min Act: -0.1700

Data Index: 8138237 (Open Web Text)

Max Activating Token Index: 649

Text #7

Max Range: 4.4020. Min Range: -4.4020

Max Act: 4.2576. Min Act: -0.1700

Data Index: 4885129 (Open Web Text)

Max Activating Token Index: 166

Text #8

Max Range: 4.4020. Min Range: -4.4020

Max Act: 4.2501. Min Act: -0.1700

Data Index: 8818115 (Open Web Text)

Max Activating Token Index: 10

Text #9

Max Range: 4.4020. Min Range: -4.4020

Max Act: 4.2851. Min Act: -0.1700

Data Index: 5176118 (Open Web Text)

Max Activating Token Index: 757

Text #10

Max Range: 4.4020. Min Range: -4.4020

Max Act: 4.2755. Min Act: -0.1700

Data Index: 33111 (Open Web Text)

Max Activating Token Index: 300

Text #11

Max Range: 4.4020. Min Range: -4.4020

Max Act: 4.2591. Min Act: -0.1700

Data Index: 1613714 (Open Web Text)

Max Activating Token Index: 708

Text #12

Max Range: 4.4020. Min Range: -4.4020

Max Act: 4.2605. Min Act: -0.1700

Data Index: 372672 (Open Web Text)

Max Activating Token Index: 86

Text #13

Max Range: 4.4020. Min Range: -4.4020

Max Act: 4.2831. Min Act: -0.1700

Data Index: 1847867 (Open Web Text)

Max Activating Token Index: 122

Text #14

Max Range: 4.4020. Min Range: -4.4020

Max Act: 4.2244. Min Act: -0.1700

Data Index: 7804127 (Open Web Text)

Max Activating Token Index: 8

Text #15

Max Range: 4.4020. Min Range: -4.4020

Max Act: 4.2596. Min Act: -0.1700

Data Index: 7110502 (Open Web Text)

Max Activating Token Index: 144

Text #16

Max Range: 4.4020. Min Range: -4.4020

Max Act: 4.2473. Min Act: -0.1700

Data Index: 6935109 (Open Web Text)

Max Activating Token Index: 740

Text #17

Max Range: 4.4020. Min Range: -4.4020

Max Act: 4.2414. Min Act: -0.1700

Data Index: 6566434 (Open Web Text)

Max Activating Token Index: 128

Text #18

Max Range: 4.4020. Min Range: -4.4020

Max Act: 4.2185. Min Act: -0.1700

Data Index: 1534905 (Open Web Text)

Max Activating Token Index: 240

Text #19

Max Range: 4.4020. Min Range: -4.4020

Max Act: 4.2143. Min Act: -0.1700

Data Index: 5678530 (Open Web Text)

Max Activating Token Index: 35