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

Dataset: Open Web Text

Neuron 1594 in Layer 1

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: 1.8977. Min Range: -1.8977

Max Act: 1.8958. Min Act: -0.1700

Data Index: 7940266 (Open Web Text)

Max Activating Token Index: 14

Text #1

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.8977. Min Act: -0.1700

Data Index: 3197578 (Open Web Text)

Max Activating Token Index: 361

Text #2

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.8644. Min Act: -0.1700

Data Index: 205534 (Open Web Text)

Max Activating Token Index: 14

Text #3

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.8743. Min Act: -0.1700

Data Index: 4509475 (Open Web Text)

Max Activating Token Index: 67

Text #4

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.8396. Min Act: -0.1700

Data Index: 6911677 (Open Web Text)

Max Activating Token Index: 72

Text #5

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.8315. Min Act: -0.1700

Data Index: 5408517 (Open Web Text)

Max Activating Token Index: 640

Text #6

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.8373. Min Act: -0.1700

Data Index: 7614336 (Open Web Text)

Max Activating Token Index: 348

Text #7

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.8198. Min Act: -0.1700

Data Index: 7709536 (Open Web Text)

Max Activating Token Index: 86

Text #8

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.8139. Min Act: -0.1700

Data Index: 1363313 (Open Web Text)

Max Activating Token Index: 808

Text #9

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.8084. Min Act: -0.1700

Data Index: 6755253 (Open Web Text)

Max Activating Token Index: 894

Text #10

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.8040. Min Act: -0.1700

Data Index: 1536033 (Open Web Text)

Max Activating Token Index: 65

Text #11

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.8178. Min Act: -0.1700

Data Index: 2926834 (Open Web Text)

Max Activating Token Index: 257

Text #12

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.7855. Min Act: -0.1700

Data Index: 1679195 (Open Web Text)

Max Activating Token Index: 947

Text #13

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.7860. Min Act: -0.1700

Data Index: 3167315 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.7963. Min Act: -0.1700

Data Index: 7571752 (Open Web Text)

Max Activating Token Index: 166

Text #15

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.7904. Min Act: -0.1700

Data Index: 5356887 (Open Web Text)

Max Activating Token Index: 8

Text #16

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.7826. Min Act: -0.1700

Data Index: 2123353 (Open Web Text)

Max Activating Token Index: 627

Text #17

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.7850. Min Act: -0.1700

Data Index: 399648 (Open Web Text)

Max Activating Token Index: 983

Text #18

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.7890. Min Act: -0.1700

Data Index: 2426398 (Open Web Text)

Max Activating Token Index: 224

Text #19

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.7843. Min Act: -0.1700

Data Index: 1776146 (Open Web Text)

Max Activating Token Index: 345