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

Dataset: Open Web Text

Neuron 1709 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: 5.0143. Min Range: -5.0143

Max Act: 5.0143. Min Act: -0.1700

Data Index: 2897212 (Open Web Text)

Max Activating Token Index: 522

Text #1

Max Range: 5.0143. Min Range: -5.0143

Max Act: 4.8827. Min Act: -0.1700

Data Index: 4422369 (Open Web Text)

Max Activating Token Index: 154

Text #2

Max Range: 5.0143. Min Range: -5.0143

Max Act: 4.9129. Min Act: -0.1700

Data Index: 6625644 (Open Web Text)

Max Activating Token Index: 942

Text #3

Max Range: 5.0143. Min Range: -5.0143

Max Act: 4.8277. Min Act: -0.1700

Data Index: 7869269 (Open Web Text)

Max Activating Token Index: 766

Text #4

Max Range: 5.0143. Min Range: -5.0143

Max Act: 4.8512. Min Act: -0.1700

Data Index: 3088628 (Open Web Text)

Max Activating Token Index: 101

Text #5

Max Range: 5.0143. Min Range: -5.0143

Max Act: 4.8245. Min Act: -0.1700

Data Index: 1880755 (Open Web Text)

Max Activating Token Index: 194

Text #6

Max Range: 5.0143. Min Range: -5.0143

Max Act: 4.8260. Min Act: -0.1700

Data Index: 6625645 (Open Web Text)

Max Activating Token Index: 131

Text #7

Max Range: 5.0143. Min Range: -5.0143

Max Act: 4.8305. Min Act: -0.1700

Data Index: 6246089 (Open Web Text)

Max Activating Token Index: 9

Text #8

Max Range: 5.0143. Min Range: -5.0143

Max Act: 4.8325. Min Act: -0.1700

Data Index: 5937258 (Open Web Text)

Max Activating Token Index: 858

Text #9

Max Range: 5.0143. Min Range: -5.0143

Max Act: 4.7847. Min Act: -0.1700

Data Index: 244413 (Open Web Text)

Max Activating Token Index: 258

Text #10

Max Range: 5.0143. Min Range: -5.0143

Max Act: 4.7960. Min Act: -0.1700

Data Index: 7908727 (Open Web Text)

Max Activating Token Index: 965

Text #11

Max Range: 5.0143. Min Range: -5.0143

Max Act: 4.7940. Min Act: -0.1700

Data Index: 2704441 (Open Web Text)

Max Activating Token Index: 435

Text #12

Max Range: 5.0143. Min Range: -5.0143

Max Act: 4.8064. Min Act: -0.1700

Data Index: 8642951 (Open Web Text)

Max Activating Token Index: 623

Text #13

Max Range: 5.0143. Min Range: -5.0143

Max Act: 4.7669. Min Act: -0.1700

Data Index: 4974184 (Open Web Text)

Max Activating Token Index: 443

Text #14

Max Range: 5.0143. Min Range: -5.0143

Max Act: 4.7591. Min Act: -0.1700

Data Index: 1140330 (Open Web Text)

Max Activating Token Index: 262

Text #15

Max Range: 5.0143. Min Range: -5.0143

Max Act: 4.7633. Min Act: -0.1700

Data Index: 4131043 (Open Web Text)

Max Activating Token Index: 195

Text #16

Max Range: 5.0143. Min Range: -5.0143

Max Act: 4.7663. Min Act: -0.1700

Data Index: 2685096 (Open Web Text)

Max Activating Token Index: 455

Text #17

Max Range: 5.0143. Min Range: -5.0143

Max Act: 4.7514. Min Act: -0.1700

Data Index: 456978 (Open Web Text)

Max Activating Token Index: 261

Text #18

Max Range: 5.0143. Min Range: -5.0143

Max Act: 4.7548. Min Act: -0.1700

Data Index: 4282041 (Open Web Text)

Max Activating Token Index: 264

Text #19

Max Range: 5.0143. Min Range: -5.0143

Max Act: 4.7119. Min Act: -0.1700

Data Index: 505831 (Open Web Text)

Max Activating Token Index: 548