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

Dataset: Open Web Text

Neuron 1200 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: 4.3972. Min Range: -4.3972

Max Act: 4.3972. Min Act: -0.1700

Data Index: 384046 (Open Web Text)

Max Activating Token Index: 502

Text #1

Max Range: 4.3972. Min Range: -4.3972

Max Act: 4.3736. Min Act: -0.1700

Data Index: 7815369 (Open Web Text)

Max Activating Token Index: 483

Text #2

Max Range: 4.3972. Min Range: -4.3972

Max Act: 4.3206. Min Act: -0.1700

Data Index: 4527120 (Open Web Text)

Max Activating Token Index: 934

Text #3

Max Range: 4.3972. Min Range: -4.3972

Max Act: 4.3201. Min Act: -0.1700

Data Index: 4721244 (Open Web Text)

Max Activating Token Index: 472

Text #4

Max Range: 4.3972. Min Range: -4.3972

Max Act: 4.2876. Min Act: -0.1700

Data Index: 454341 (Open Web Text)

Max Activating Token Index: 126

Text #5

Max Range: 4.3972. Min Range: -4.3972

Max Act: 4.2636. Min Act: -0.1700

Data Index: 5529724 (Open Web Text)

Max Activating Token Index: 475

Text #6

Max Range: 4.3972. Min Range: -4.3972

Max Act: 4.2996. Min Act: -0.1700

Data Index: 3147969 (Open Web Text)

Max Activating Token Index: 30

Text #7

Max Range: 4.3972. Min Range: -4.3972

Max Act: 4.3053. Min Act: -0.1700

Data Index: 3247878 (Open Web Text)

Max Activating Token Index: 24

Text #8

Max Range: 4.3972. Min Range: -4.3972

Max Act: 4.2480. Min Act: -0.1700

Data Index: 4294135 (Open Web Text)

Max Activating Token Index: 92

Text #9

Max Range: 4.3972. Min Range: -4.3972

Max Act: 4.2284. Min Act: -0.1700

Data Index: 7637894 (Open Web Text)

Max Activating Token Index: 230

Text #10

Max Range: 4.3972. Min Range: -4.3972

Max Act: 4.2210. Min Act: -0.1700

Data Index: 572399 (Open Web Text)

Max Activating Token Index: 239

Text #11

Max Range: 4.3972. Min Range: -4.3972

Max Act: 4.1132. Min Act: -0.1700

Data Index: 7123422 (Open Web Text)

Max Activating Token Index: 651

Text #12

Max Range: 4.3972. Min Range: -4.3972

Max Act: 4.1480. Min Act: -0.1700

Data Index: 5839920 (Open Web Text)

Max Activating Token Index: 330

Text #13

Max Range: 4.3972. Min Range: -4.3972

Max Act: 4.1924. Min Act: -0.1700

Data Index: 3551016 (Open Web Text)

Max Activating Token Index: 375

Text #14

Max Range: 4.3972. Min Range: -4.3972

Max Act: 4.2012. Min Act: -0.1700

Data Index: 4401083 (Open Web Text)

Max Activating Token Index: 650

Text #15

Max Range: 4.3972. Min Range: -4.3972

Max Act: 4.1670. Min Act: -0.1700

Data Index: 3953494 (Open Web Text)

Max Activating Token Index: 15

Text #16

Max Range: 4.3972. Min Range: -4.3972

Max Act: 4.1790. Min Act: -0.1700

Data Index: 1987701 (Open Web Text)

Max Activating Token Index: 425

Text #17

Max Range: 4.3972. Min Range: -4.3972

Max Act: 4.1863. Min Act: -0.1700

Data Index: 4243330 (Open Web Text)

Max Activating Token Index: 189

Text #18

Max Range: 4.3972. Min Range: -4.3972

Max Act: 4.1704. Min Act: -0.1700

Data Index: 7704285 (Open Web Text)

Max Activating Token Index: 64

Text #19

Max Range: 4.3972. Min Range: -4.3972

Max Act: 4.1978. Min Act: -0.1700

Data Index: 432508 (Open Web Text)

Max Activating Token Index: 539