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

Dataset: Open Web Text

Neuron 1604 in Layer 4

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: 3.0158. Min Range: -3.0158

Max Act: 3.0158. Min Act: -0.1700

Data Index: 6909375 (Open Web Text)

Max Activating Token Index: 951

Text #1

Max Range: 3.0158. Min Range: -3.0158

Max Act: 3.0004. Min Act: -0.1700

Data Index: 3929618 (Open Web Text)

Max Activating Token Index: 215

Text #2

Max Range: 3.0158. Min Range: -3.0158

Max Act: 2.9674. Min Act: -0.1700

Data Index: 1230858 (Open Web Text)

Max Activating Token Index: 774

Text #3

Max Range: 3.0158. Min Range: -3.0158

Max Act: 2.9351. Min Act: -0.1700

Data Index: 7646874 (Open Web Text)

Max Activating Token Index: 889

Text #4

Max Range: 3.0158. Min Range: -3.0158

Max Act: 2.9315. Min Act: -0.1700

Data Index: 3277961 (Open Web Text)

Max Activating Token Index: 11

Text #5

Max Range: 3.0158. Min Range: -3.0158

Max Act: 2.9232. Min Act: -0.1700

Data Index: 5916382 (Open Web Text)

Max Activating Token Index: 869

Text #6

Max Range: 3.0158. Min Range: -3.0158

Max Act: 2.9205. Min Act: -0.1700

Data Index: 8561289 (Open Web Text)

Max Activating Token Index: 207

Text #7

Max Range: 3.0158. Min Range: -3.0158

Max Act: 2.8852. Min Act: -0.1700

Data Index: 2396984 (Open Web Text)

Max Activating Token Index: 538

Text #8

Max Range: 3.0158. Min Range: -3.0158

Max Act: 2.8153. Min Act: -0.1700

Data Index: 3081450 (Open Web Text)

Max Activating Token Index: 913

Text #9

Max Range: 3.0158. Min Range: -3.0158

Max Act: 2.8060. Min Act: -0.1700

Data Index: 1765091 (Open Web Text)

Max Activating Token Index: 416

Text #10

Max Range: 3.0158. Min Range: -3.0158

Max Act: 2.8034. Min Act: -0.1700

Data Index: 7368223 (Open Web Text)

Max Activating Token Index: 133

Text #11

Max Range: 3.0158. Min Range: -3.0158

Max Act: 2.7633. Min Act: -0.1700

Data Index: 907004 (Open Web Text)

Max Activating Token Index: 438

Text #12

Max Range: 3.0158. Min Range: -3.0158

Max Act: 2.7620. Min Act: -0.1700

Data Index: 8239767 (Open Web Text)

Max Activating Token Index: 294

Text #13

Max Range: 3.0158. Min Range: -3.0158

Max Act: 2.7687. Min Act: -0.1700

Data Index: 2587322 (Open Web Text)

Max Activating Token Index: 593

Text #14

Max Range: 3.0158. Min Range: -3.0158

Max Act: 2.7695. Min Act: -0.1700

Data Index: 8131869 (Open Web Text)

Max Activating Token Index: 175

Text #15

Max Range: 3.0158. Min Range: -3.0158

Max Act: 2.7279. Min Act: -0.1700

Data Index: 4982488 (Open Web Text)

Max Activating Token Index: 951

Text #16

Max Range: 3.0158. Min Range: -3.0158

Max Act: 2.7284. Min Act: -0.1700

Data Index: 7634919 (Open Web Text)

Max Activating Token Index: 769

Text #17

Max Range: 3.0158. Min Range: -3.0158

Max Act: 2.7282. Min Act: -0.1700

Data Index: 5363688 (Open Web Text)

Max Activating Token Index: 524

Text #18

Max Range: 3.0158. Min Range: -3.0158

Max Act: 2.7187. Min Act: -0.1700

Data Index: 2971363 (Open Web Text)

Max Activating Token Index: 14

Text #19

Max Range: 3.0158. Min Range: -3.0158

Max Act: 2.7202. Min Act: -0.1700

Data Index: 6708076 (Open Web Text)

Max Activating Token Index: 802