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

Dataset: Open Web Text

Neuron 2231 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: 5.2574. Min Range: -5.2574

Max Act: 5.0998. Min Act: -0.1700

Data Index: 1666513 (Open Web Text)

Max Activating Token Index: 212

Text #1

Max Range: 5.2574. Min Range: -5.2574

Max Act: 5.2574. Min Act: -0.1700

Data Index: 5439384 (Open Web Text)

Max Activating Token Index: 152

Text #2

Max Range: 5.2574. Min Range: -5.2574

Max Act: 5.0298. Min Act: -0.1700

Data Index: 4437601 (Open Web Text)

Max Activating Token Index: 792

Text #3

Max Range: 5.2574. Min Range: -5.2574

Max Act: 4.9742. Min Act: -0.1700

Data Index: 1771317 (Open Web Text)

Max Activating Token Index: 867

Text #4

Max Range: 5.2574. Min Range: -5.2574

Max Act: 4.9348. Min Act: -0.1700

Data Index: 2649489 (Open Web Text)

Max Activating Token Index: 178

Text #5

Max Range: 5.2574. Min Range: -5.2574

Max Act: 4.9362. Min Act: -0.1700

Data Index: 1715163 (Open Web Text)

Max Activating Token Index: 989

Text #6

Max Range: 5.2574. Min Range: -5.2574

Max Act: 4.9514. Min Act: -0.1700

Data Index: 3520646 (Open Web Text)

Max Activating Token Index: 765

Text #7

Max Range: 5.2574. Min Range: -5.2574

Max Act: 4.9043. Min Act: -0.1700

Data Index: 5872288 (Open Web Text)

Max Activating Token Index: 546

Text #8

Max Range: 5.2574. Min Range: -5.2574

Max Act: 4.8833. Min Act: -0.1700

Data Index: 6732039 (Open Web Text)

Max Activating Token Index: 222

Text #9

Max Range: 5.2574. Min Range: -5.2574

Max Act: 4.9688. Min Act: -0.1700

Data Index: 4779552 (Open Web Text)

Max Activating Token Index: 482

Text #10

Max Range: 5.2574. Min Range: -5.2574

Max Act: 4.8343. Min Act: -0.1700

Data Index: 4847191 (Open Web Text)

Max Activating Token Index: 673

Text #11

Max Range: 5.2574. Min Range: -5.2574

Max Act: 4.8707. Min Act: -0.1700

Data Index: 7165791 (Open Web Text)

Max Activating Token Index: 400

Text #12

Max Range: 5.2574. Min Range: -5.2574

Max Act: 4.8620. Min Act: -0.1700

Data Index: 6430278 (Open Web Text)

Max Activating Token Index: 146

Text #13

Max Range: 5.2574. Min Range: -5.2574

Max Act: 4.7975. Min Act: -0.1700

Data Index: 2396170 (Open Web Text)

Max Activating Token Index: 127

Text #14

Max Range: 5.2574. Min Range: -5.2574

Max Act: 4.8059. Min Act: -0.1700

Data Index: 350890 (Open Web Text)

Max Activating Token Index: 515

Text #15

Max Range: 5.2574. Min Range: -5.2574

Max Act: 4.8377. Min Act: -0.1700

Data Index: 5615786 (Open Web Text)

Max Activating Token Index: 140

Text #16

Max Range: 5.2574. Min Range: -5.2574

Max Act: 4.8259. Min Act: -0.1700

Data Index: 2029042 (Open Web Text)

Max Activating Token Index: 29

Text #17

Max Range: 5.2574. Min Range: -5.2574

Max Act: 4.7269. Min Act: -0.1700

Data Index: 6427347 (Open Web Text)

Max Activating Token Index: 192

Text #18

Max Range: 5.2574. Min Range: -5.2574

Max Act: 4.6961. Min Act: -0.1700

Data Index: 2622287 (Open Web Text)

Max Activating Token Index: 537

Text #19

Max Range: 5.2574. Min Range: -5.2574

Max Act: 4.7862. Min Act: -0.1700

Data Index: 1481486 (Open Web Text)

Max Activating Token Index: 898