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

Dataset: Open Web Text

Neuron 985 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: 3.8512. Min Range: -3.8512

Max Act: 3.8512. Min Act: -0.1700

Data Index: 965144 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 3.8512. Min Range: -3.8512

Max Act: 3.8227. Min Act: -0.1700

Data Index: 5763811 (Open Web Text)

Max Activating Token Index: 972

Text #2

Max Range: 3.8512. Min Range: -3.8512

Max Act: 3.8262. Min Act: -0.1700

Data Index: 298031 (Open Web Text)

Max Activating Token Index: 417

Text #3

Max Range: 3.8512. Min Range: -3.8512

Max Act: 3.8151. Min Act: -0.1700

Data Index: 5397565 (Open Web Text)

Max Activating Token Index: 860

Text #4

Max Range: 3.8512. Min Range: -3.8512

Max Act: 3.8169. Min Act: -0.1700

Data Index: 5394324 (Open Web Text)

Max Activating Token Index: 657

Text #5

Max Range: 3.8512. Min Range: -3.8512

Max Act: 3.8133. Min Act: -0.1700

Data Index: 4691870 (Open Web Text)

Max Activating Token Index: 999

Text #6

Max Range: 3.8512. Min Range: -3.8512

Max Act: 3.8112. Min Act: -0.1700

Data Index: 4616811 (Open Web Text)

Max Activating Token Index: 564

Text #7

Max Range: 3.8512. Min Range: -3.8512

Max Act: 3.8236. Min Act: -0.1700

Data Index: 4603961 (Open Web Text)

Max Activating Token Index: 991

Text #8

Max Range: 3.8512. Min Range: -3.8512

Max Act: 3.8293. Min Act: -0.1700

Data Index: 4414280 (Open Web Text)

Max Activating Token Index: 993

Text #9

Max Range: 3.8512. Min Range: -3.8512

Max Act: 3.8283. Min Act: -0.1700

Data Index: 4129221 (Open Web Text)

Max Activating Token Index: 985

Text #10

Max Range: 3.8512. Min Range: -3.8512

Max Act: 3.8300. Min Act: -0.1700

Data Index: 3618108 (Open Web Text)

Max Activating Token Index: 923

Text #11

Max Range: 3.8512. Min Range: -3.8512

Max Act: 3.8191. Min Act: -0.1700

Data Index: 3364107 (Open Web Text)

Max Activating Token Index: 981

Text #12

Max Range: 3.8512. Min Range: -3.8512

Max Act: 3.8232. Min Act: -0.1700

Data Index: 3217402 (Open Web Text)

Max Activating Token Index: 965

Text #13

Max Range: 3.8512. Min Range: -3.8512

Max Act: 3.8112. Min Act: -0.1700

Data Index: 3196759 (Open Web Text)

Max Activating Token Index: 564

Text #14

Max Range: 3.8512. Min Range: -3.8512

Max Act: 3.8187. Min Act: -0.1700

Data Index: 3013744 (Open Web Text)

Max Activating Token Index: 983

Text #15

Max Range: 3.8512. Min Range: -3.8512

Max Act: 3.8112. Min Act: -0.1700

Data Index: 2994300 (Open Web Text)

Max Activating Token Index: 564

Text #16

Max Range: 3.8512. Min Range: -3.8512

Max Act: 3.8213. Min Act: -0.1700

Data Index: 2803654 (Open Web Text)

Max Activating Token Index: 732

Text #17

Max Range: 3.8512. Min Range: -3.8512

Max Act: 3.8151. Min Act: -0.1700

Data Index: 2725252 (Open Web Text)

Max Activating Token Index: 860

Text #18

Max Range: 3.8512. Min Range: -3.8512

Max Act: 3.8198. Min Act: -0.1700

Data Index: 2114747 (Open Web Text)

Max Activating Token Index: 950

Text #19

Max Range: 3.8512. Min Range: -3.8512

Max Act: 3.8188. Min Act: -0.1700

Data Index: 2114749 (Open Web Text)

Max Activating Token Index: 943