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

Dataset: Open Web Text

Neuron 51 in Layer 2

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: 1.9167. Min Range: -1.9167

Max Act: 1.9167. Min Act: -0.1700

Data Index: 1903560 (Open Web Text)

Max Activating Token Index: 869

Text #1

Max Range: 1.9167. Min Range: -1.9167

Max Act: 1.8952. Min Act: -0.1700

Data Index: 5775482 (Open Web Text)

Max Activating Token Index: 298

Text #2

Max Range: 1.9167. Min Range: -1.9167

Max Act: 1.8667. Min Act: -0.1700

Data Index: 5755958 (Open Web Text)

Max Activating Token Index: 552

Text #3

Max Range: 1.9167. Min Range: -1.9167

Max Act: 1.8786. Min Act: -0.1700

Data Index: 1314332 (Open Web Text)

Max Activating Token Index: 808

Text #4

Max Range: 1.9167. Min Range: -1.9167

Max Act: 1.8856. Min Act: -0.1700

Data Index: 6007932 (Open Web Text)

Max Activating Token Index: 181

Text #5

Max Range: 1.9167. Min Range: -1.9167

Max Act: 1.8716. Min Act: -0.1700

Data Index: 7518859 (Open Web Text)

Max Activating Token Index: 962

Text #6

Max Range: 1.9167. Min Range: -1.9167

Max Act: 1.8620. Min Act: -0.1700

Data Index: 5847161 (Open Web Text)

Max Activating Token Index: 243

Text #7

Max Range: 1.9167. Min Range: -1.9167

Max Act: 1.8613. Min Act: -0.1700

Data Index: 1940429 (Open Web Text)

Max Activating Token Index: 532

Text #8

Max Range: 1.9167. Min Range: -1.9167

Max Act: 1.8635. Min Act: -0.1700

Data Index: 6525095 (Open Web Text)

Max Activating Token Index: 427

Text #9

Max Range: 1.9167. Min Range: -1.9167

Max Act: 1.8678. Min Act: -0.1700

Data Index: 545625 (Open Web Text)

Max Activating Token Index: 453

Text #10

Max Range: 1.9167. Min Range: -1.9167

Max Act: 1.8677. Min Act: -0.1700

Data Index: 8460661 (Open Web Text)

Max Activating Token Index: 36

Text #11

Max Range: 1.9167. Min Range: -1.9167

Max Act: 1.8489. Min Act: -0.1700

Data Index: 8409235 (Open Web Text)

Max Activating Token Index: 591

Text #12

Max Range: 1.9167. Min Range: -1.9167

Max Act: 1.8520. Min Act: -0.1700

Data Index: 6147560 (Open Web Text)

Max Activating Token Index: 1014

Text #13

Max Range: 1.9167. Min Range: -1.9167

Max Act: 1.8512. Min Act: -0.1700

Data Index: 1058798 (Open Web Text)

Max Activating Token Index: 986

Text #14

Max Range: 1.9167. Min Range: -1.9167

Max Act: 1.8506. Min Act: -0.1700

Data Index: 6559013 (Open Web Text)

Max Activating Token Index: 949

Text #15

Max Range: 1.9167. Min Range: -1.9167

Max Act: 1.8450. Min Act: -0.1700

Data Index: 3347356 (Open Web Text)

Max Activating Token Index: 913

Text #16

Max Range: 1.9167. Min Range: -1.9167

Max Act: 1.8362. Min Act: -0.1700

Data Index: 6685317 (Open Web Text)

Max Activating Token Index: 995

Text #17

Max Range: 1.9167. Min Range: -1.9167

Max Act: 1.8382. Min Act: -0.1700

Data Index: 7297209 (Open Web Text)

Max Activating Token Index: 590

Text #18

Max Range: 1.9167. Min Range: -1.9167

Max Act: 1.8371. Min Act: -0.1700

Data Index: 6647585 (Open Web Text)

Max Activating Token Index: 313

Text #19

Max Range: 1.9167. Min Range: -1.9167

Max Act: 1.8243. Min Act: -0.1700

Data Index: 7871729 (Open Web Text)

Max Activating Token Index: 683