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

Dataset: Open Web Text

Neuron 1378 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: 3.3288. Min Range: -3.3288

Max Act: 3.3288. Min Act: -0.1700

Data Index: 1983252 (Open Web Text)

Max Activating Token Index: 183

Text #1

Max Range: 3.3288. Min Range: -3.3288

Max Act: 3.3110. Min Act: -0.1700

Data Index: 8014078 (Open Web Text)

Max Activating Token Index: 794

Text #2

Max Range: 3.3288. Min Range: -3.3288

Max Act: 3.2784. Min Act: -0.1700

Data Index: 4947112 (Open Web Text)

Max Activating Token Index: 900

Text #3

Max Range: 3.3288. Min Range: -3.3288

Max Act: 3.2277. Min Act: -0.1700

Data Index: 1408473 (Open Web Text)

Max Activating Token Index: 162

Text #4

Max Range: 3.3288. Min Range: -3.3288

Max Act: 3.2265. Min Act: -0.1700

Data Index: 565235 (Open Web Text)

Max Activating Token Index: 31

Text #5

Max Range: 3.3288. Min Range: -3.3288

Max Act: 3.1967. Min Act: -0.1700

Data Index: 3842984 (Open Web Text)

Max Activating Token Index: 473

Text #6

Max Range: 3.3288. Min Range: -3.3288

Max Act: 3.1986. Min Act: -0.1700

Data Index: 7574577 (Open Web Text)

Max Activating Token Index: 161

Text #7

Max Range: 3.3288. Min Range: -3.3288

Max Act: 3.2200. Min Act: -0.1700

Data Index: 5782294 (Open Web Text)

Max Activating Token Index: 316

Text #8

Max Range: 3.3288. Min Range: -3.3288

Max Act: 3.1802. Min Act: -0.1700

Data Index: 6941647 (Open Web Text)

Max Activating Token Index: 375

Text #9

Max Range: 3.3288. Min Range: -3.3288

Max Act: 3.1549. Min Act: -0.1700

Data Index: 8406266 (Open Web Text)

Max Activating Token Index: 876

Text #10

Max Range: 3.3288. Min Range: -3.3288

Max Act: 3.1564. Min Act: -0.1700

Data Index: 223177 (Open Web Text)

Max Activating Token Index: 596

Text #11

Max Range: 3.3288. Min Range: -3.3288

Max Act: 3.1438. Min Act: -0.1700

Data Index: 2296763 (Open Web Text)

Max Activating Token Index: 973

Text #12

Max Range: 3.3288. Min Range: -3.3288

Max Act: 3.1366. Min Act: -0.1700

Data Index: 4743141 (Open Web Text)

Max Activating Token Index: 588

Text #13

Max Range: 3.3288. Min Range: -3.3288

Max Act: 3.1199. Min Act: -0.1700

Data Index: 1106917 (Open Web Text)

Max Activating Token Index: 238

Text #14

Max Range: 3.3288. Min Range: -3.3288

Max Act: 3.1519. Min Act: -0.1700

Data Index: 6033538 (Open Web Text)

Max Activating Token Index: 281

Text #15

Max Range: 3.3288. Min Range: -3.3288

Max Act: 3.0708. Min Act: -0.1700

Data Index: 4019797 (Open Web Text)

Max Activating Token Index: 929

Text #16

Max Range: 3.3288. Min Range: -3.3288

Max Act: 3.1254. Min Act: -0.1700

Data Index: 8494551 (Open Web Text)

Max Activating Token Index: 10

Text #17

Max Range: 3.3288. Min Range: -3.3288

Max Act: 3.1516. Min Act: -0.1700

Data Index: 3545743 (Open Web Text)

Max Activating Token Index: 602

Text #18

Max Range: 3.3288. Min Range: -3.3288

Max Act: 3.0789. Min Act: -0.1700

Data Index: 3185998 (Open Web Text)

Max Activating Token Index: 875

Text #19

Max Range: 3.3288. Min Range: -3.3288

Max Act: 3.0826. Min Act: -0.1700

Data Index: 1435428 (Open Web Text)

Max Activating Token Index: 294