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

Dataset: Open Web Text

Neuron 2296 in Layer 0

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: 3.3183. Min Range: -3.3183

Max Act: 3.3183. Min Act: -0.1700

Data Index: 5930428 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 3.3183. Min Range: -3.3183

Max Act: 3.2499. Min Act: -0.1700

Data Index: 2324909 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.3183. Min Range: -3.3183

Max Act: 3.1857. Min Act: -0.1700

Data Index: 4467193 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 3.3183. Min Range: -3.3183

Max Act: 3.1703. Min Act: -0.1700

Data Index: 6290624 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 3.3183. Min Range: -3.3183

Max Act: 3.1637. Min Act: -0.1700

Data Index: 2132647 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 3.3183. Min Range: -3.3183

Max Act: 3.1570. Min Act: -0.1700

Data Index: 4568288 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 3.3183. Min Range: -3.3183

Max Act: 3.1602. Min Act: -0.1700

Data Index: 4173750 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 3.3183. Min Range: -3.3183

Max Act: 3.1589. Min Act: -0.1700

Data Index: 8239534 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 3.3183. Min Range: -3.3183

Max Act: 3.1508. Min Act: -0.1700

Data Index: 3404555 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.3183. Min Range: -3.3183

Max Act: 3.1537. Min Act: -0.1700

Data Index: 8043624 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 3.3183. Min Range: -3.3183

Max Act: 3.1360. Min Act: -0.1700

Data Index: 4704633 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 3.3183. Min Range: -3.3183

Max Act: 3.1297. Min Act: -0.1700

Data Index: 1211419 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 3.3183. Min Range: -3.3183

Max Act: 3.1336. Min Act: -0.1700

Data Index: 1236570 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 3.3183. Min Range: -3.3183

Max Act: 3.1275. Min Act: -0.1700

Data Index: 1077317 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 3.3183. Min Range: -3.3183

Max Act: 3.1136. Min Act: -0.1700

Data Index: 3328517 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 3.3183. Min Range: -3.3183

Max Act: 3.1074. Min Act: -0.1700

Data Index: 5876995 (Open Web Text)

Max Activating Token Index: 8

Text #16

Max Range: 3.3183. Min Range: -3.3183

Max Act: 3.1213. Min Act: -0.1700

Data Index: 5692826 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 3.3183. Min Range: -3.3183

Max Act: 3.0867. Min Act: -0.1700

Data Index: 3043706 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 3.3183. Min Range: -3.3183

Max Act: 3.1047. Min Act: -0.1700

Data Index: 763658 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 3.3183. Min Range: -3.3183

Max Act: 3.0974. Min Act: -0.1700

Data Index: 1079257 (Open Web Text)

Max Activating Token Index: 3