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

Dataset: Open Web Text

Neuron 293 in Layer 3

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: 3.5725. Min Range: -3.5725

Max Act: 3.5725. Min Act: -0.1700

Data Index: 4851215 (Open Web Text)

Max Activating Token Index: 292

Text #1

Max Range: 3.5725. Min Range: -3.5725

Max Act: 3.5469. Min Act: -0.1700

Data Index: 1910632 (Open Web Text)

Max Activating Token Index: 208

Text #2

Max Range: 3.5725. Min Range: -3.5725

Max Act: 3.5006. Min Act: -0.1700

Data Index: 2518972 (Open Web Text)

Max Activating Token Index: 664

Text #3

Max Range: 3.5725. Min Range: -3.5725

Max Act: 3.5084. Min Act: -0.1700

Data Index: 7939077 (Open Web Text)

Max Activating Token Index: 928

Text #4

Max Range: 3.5725. Min Range: -3.5725

Max Act: 3.5121. Min Act: -0.1700

Data Index: 317672 (Open Web Text)

Max Activating Token Index: 195

Text #5

Max Range: 3.5725. Min Range: -3.5725

Max Act: 3.4790. Min Act: -0.1700

Data Index: 7637922 (Open Web Text)

Max Activating Token Index: 585

Text #6

Max Range: 3.5725. Min Range: -3.5725

Max Act: 3.4515. Min Act: -0.1700

Data Index: 2434262 (Open Web Text)

Max Activating Token Index: 288

Text #7

Max Range: 3.5725. Min Range: -3.5725

Max Act: 3.4467. Min Act: -0.1700

Data Index: 2046346 (Open Web Text)

Max Activating Token Index: 171

Text #8

Max Range: 3.5725. Min Range: -3.5725

Max Act: 3.4034. Min Act: -0.1700

Data Index: 8049970 (Open Web Text)

Max Activating Token Index: 342

Text #9

Max Range: 3.5725. Min Range: -3.5725

Max Act: 3.3275. Min Act: -0.1700

Data Index: 8697874 (Open Web Text)

Max Activating Token Index: 43

Text #10

Max Range: 3.5725. Min Range: -3.5725

Max Act: 3.3595. Min Act: -0.1700

Data Index: 5711714 (Open Web Text)

Max Activating Token Index: 90

Text #11

Max Range: 3.5725. Min Range: -3.5725

Max Act: 3.3001. Min Act: -0.1700

Data Index: 6035551 (Open Web Text)

Max Activating Token Index: 200

Text #12

Max Range: 3.5725. Min Range: -3.5725

Max Act: 3.2942. Min Act: -0.1700

Data Index: 6855098 (Open Web Text)

Max Activating Token Index: 524

Text #13

Max Range: 3.5725. Min Range: -3.5725

Max Act: 3.3012. Min Act: -0.1700

Data Index: 7224307 (Open Web Text)

Max Activating Token Index: 299

Text #14

Max Range: 3.5725. Min Range: -3.5725

Max Act: 3.2790. Min Act: -0.1700

Data Index: 7014026 (Open Web Text)

Max Activating Token Index: 218

Text #15

Max Range: 3.5725. Min Range: -3.5725

Max Act: 3.2873. Min Act: -0.1700

Data Index: 6035541 (Open Web Text)

Max Activating Token Index: 121

Text #16

Max Range: 3.5725. Min Range: -3.5725

Max Act: 3.2415. Min Act: -0.1700

Data Index: 3327782 (Open Web Text)

Max Activating Token Index: 725

Text #17

Max Range: 3.5725. Min Range: -3.5725

Max Act: 3.2472. Min Act: -0.1700

Data Index: 3896857 (Open Web Text)

Max Activating Token Index: 125

Text #18

Max Range: 3.5725. Min Range: -3.5725

Max Act: 3.2520. Min Act: -0.1700

Data Index: 2205342 (Open Web Text)

Max Activating Token Index: 910

Text #19

Max Range: 3.5725. Min Range: -3.5725

Max Act: 3.2433. Min Act: -0.1700

Data Index: 2284225 (Open Web Text)

Max Activating Token Index: 84