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

Dataset: Open Web Text

Neuron 407 in Layer 6

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: 4.3121. Min Range: -4.3121

Max Act: 4.3121. Min Act: -0.1700

Data Index: 5508702 (Open Web Text)

Max Activating Token Index: 489

Text #1

Max Range: 4.3121. Min Range: -4.3121

Max Act: 4.3064. Min Act: -0.1700

Data Index: 2670828 (Open Web Text)

Max Activating Token Index: 214

Text #2

Max Range: 4.3121. Min Range: -4.3121

Max Act: 4.2266. Min Act: -0.1700

Data Index: 590728 (Open Web Text)

Max Activating Token Index: 946

Text #3

Max Range: 4.3121. Min Range: -4.3121

Max Act: 4.2352. Min Act: -0.1700

Data Index: 8693702 (Open Web Text)

Max Activating Token Index: 1004

Text #4

Max Range: 4.3121. Min Range: -4.3121

Max Act: 4.2045. Min Act: -0.1700

Data Index: 1147658 (Open Web Text)

Max Activating Token Index: 1005

Text #5

Max Range: 4.3121. Min Range: -4.3121

Max Act: 4.2248. Min Act: -0.1700

Data Index: 6485271 (Open Web Text)

Max Activating Token Index: 348

Text #6

Max Range: 4.3121. Min Range: -4.3121

Max Act: 4.1641. Min Act: -0.1700

Data Index: 1780287 (Open Web Text)

Max Activating Token Index: 686

Text #7

Max Range: 4.3121. Min Range: -4.3121

Max Act: 4.1717. Min Act: -0.1700

Data Index: 3591080 (Open Web Text)

Max Activating Token Index: 428

Text #8

Max Range: 4.3121. Min Range: -4.3121

Max Act: 4.1334. Min Act: -0.1700

Data Index: 5791863 (Open Web Text)

Max Activating Token Index: 528

Text #9

Max Range: 4.3121. Min Range: -4.3121

Max Act: 4.1137. Min Act: -0.1700

Data Index: 3404892 (Open Web Text)

Max Activating Token Index: 743

Text #10

Max Range: 4.3121. Min Range: -4.3121

Max Act: 4.1229. Min Act: -0.1700

Data Index: 6582660 (Open Web Text)

Max Activating Token Index: 323

Text #11

Max Range: 4.3121. Min Range: -4.3121

Max Act: 4.0953. Min Act: -0.1700

Data Index: 3809324 (Open Web Text)

Max Activating Token Index: 358

Text #12

Max Range: 4.3121. Min Range: -4.3121

Max Act: 4.0967. Min Act: -0.1700

Data Index: 3182735 (Open Web Text)

Max Activating Token Index: 930

Text #13

Max Range: 4.3121. Min Range: -4.3121

Max Act: 4.0689. Min Act: -0.1700

Data Index: 6251904 (Open Web Text)

Max Activating Token Index: 163

Text #14

Max Range: 4.3121. Min Range: -4.3121

Max Act: 4.0950. Min Act: -0.1700

Data Index: 7796905 (Open Web Text)

Max Activating Token Index: 866

Text #15

Max Range: 4.3121. Min Range: -4.3121

Max Act: 4.0613. Min Act: -0.1700

Data Index: 8671808 (Open Web Text)

Max Activating Token Index: 634

Text #16

Max Range: 4.3121. Min Range: -4.3121

Max Act: 4.1050. Min Act: -0.1700

Data Index: 5787051 (Open Web Text)

Max Activating Token Index: 970

Text #17

Max Range: 4.3121. Min Range: -4.3121

Max Act: 4.0632. Min Act: -0.1700

Data Index: 3553165 (Open Web Text)

Max Activating Token Index: 67

Text #18

Max Range: 4.3121. Min Range: -4.3121

Max Act: 4.0539. Min Act: -0.1700

Data Index: 5264861 (Open Web Text)

Max Activating Token Index: 631

Text #19

Max Range: 4.3121. Min Range: -4.3121

Max Act: 4.0489. Min Act: -0.1700

Data Index: 6323051 (Open Web Text)

Max Activating Token Index: 175