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

Dataset: Open Web Text

Neuron 730 in Layer 5

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: 3.3965. Min Range: -3.3965

Max Act: 3.3965. Min Act: -0.1700

Data Index: 302562 (Open Web Text)

Max Activating Token Index: 871

Text #1

Max Range: 3.3965. Min Range: -3.3965

Max Act: 3.0886. Min Act: -0.1700

Data Index: 149056 (Open Web Text)

Max Activating Token Index: 315

Text #2

Max Range: 3.3965. Min Range: -3.3965

Max Act: 3.0709. Min Act: -0.1700

Data Index: 1522064 (Open Web Text)

Max Activating Token Index: 433

Text #3

Max Range: 3.3965. Min Range: -3.3965

Max Act: 3.0485. Min Act: -0.1700

Data Index: 7330882 (Open Web Text)

Max Activating Token Index: 536

Text #4

Max Range: 3.3965. Min Range: -3.3965

Max Act: 3.0500. Min Act: -0.1700

Data Index: 7527100 (Open Web Text)

Max Activating Token Index: 403

Text #5

Max Range: 3.3965. Min Range: -3.3965

Max Act: 3.0164. Min Act: -0.1700

Data Index: 6746254 (Open Web Text)

Max Activating Token Index: 966

Text #6

Max Range: 3.3965. Min Range: -3.3965

Max Act: 2.9912. Min Act: -0.1700

Data Index: 8701942 (Open Web Text)

Max Activating Token Index: 598

Text #7

Max Range: 3.3965. Min Range: -3.3965

Max Act: 3.0093. Min Act: -0.1700

Data Index: 6244465 (Open Web Text)

Max Activating Token Index: 554

Text #8

Max Range: 3.3965. Min Range: -3.3965

Max Act: 3.0302. Min Act: -0.1700

Data Index: 1570910 (Open Web Text)

Max Activating Token Index: 699

Text #9

Max Range: 3.3965. Min Range: -3.3965

Max Act: 3.0114. Min Act: -0.1700

Data Index: 350310 (Open Web Text)

Max Activating Token Index: 422

Text #10

Max Range: 3.3965. Min Range: -3.3965

Max Act: 3.0012. Min Act: -0.1700

Data Index: 5161188 (Open Web Text)

Max Activating Token Index: 468

Text #11

Max Range: 3.3965. Min Range: -3.3965

Max Act: 2.9888. Min Act: -0.1700

Data Index: 4380039 (Open Web Text)

Max Activating Token Index: 946

Text #12

Max Range: 3.3965. Min Range: -3.3965

Max Act: 2.9842. Min Act: -0.1700

Data Index: 1358939 (Open Web Text)

Max Activating Token Index: 313

Text #13

Max Range: 3.3965. Min Range: -3.3965

Max Act: 2.9723. Min Act: -0.1700

Data Index: 218051 (Open Web Text)

Max Activating Token Index: 819

Text #14

Max Range: 3.3965. Min Range: -3.3965

Max Act: 2.9942. Min Act: -0.1700

Data Index: 1871168 (Open Web Text)

Max Activating Token Index: 210

Text #15

Max Range: 3.3965. Min Range: -3.3965

Max Act: 2.9538. Min Act: -0.1700

Data Index: 7852169 (Open Web Text)

Max Activating Token Index: 436

Text #16

Max Range: 3.3965. Min Range: -3.3965

Max Act: 2.9520. Min Act: -0.1700

Data Index: 1541184 (Open Web Text)

Max Activating Token Index: 211

Text #17

Max Range: 3.3965. Min Range: -3.3965

Max Act: 2.9475. Min Act: -0.1700

Data Index: 1923434 (Open Web Text)

Max Activating Token Index: 677

Text #18

Max Range: 3.3965. Min Range: -3.3965

Max Act: 2.9809. Min Act: -0.1700

Data Index: 1533079 (Open Web Text)

Max Activating Token Index: 253

Text #19

Max Range: 3.3965. Min Range: -3.3965

Max Act: 2.9522. Min Act: -0.1700

Data Index: 4048881 (Open Web Text)

Max Activating Token Index: 562