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

Dataset: Open Web Text

Neuron 1058 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: 3.1637. Min Range: -3.1637

Max Act: 3.1637. Min Act: -0.1700

Data Index: 574328 (Open Web Text)

Max Activating Token Index: 775

Text #1

Max Range: 3.1637. Min Range: -3.1637

Max Act: 3.1222. Min Act: -0.1700

Data Index: 1259995 (Open Web Text)

Max Activating Token Index: 905

Text #2

Max Range: 3.1637. Min Range: -3.1637

Max Act: 3.0622. Min Act: -0.1700

Data Index: 432039 (Open Web Text)

Max Activating Token Index: 962

Text #3

Max Range: 3.1637. Min Range: -3.1637

Max Act: 3.0663. Min Act: -0.1700

Data Index: 1763735 (Open Web Text)

Max Activating Token Index: 211

Text #4

Max Range: 3.1637. Min Range: -3.1637

Max Act: 2.9950. Min Act: -0.1700

Data Index: 7929872 (Open Web Text)

Max Activating Token Index: 182

Text #5

Max Range: 3.1637. Min Range: -3.1637

Max Act: 2.9639. Min Act: -0.1700

Data Index: 6428300 (Open Web Text)

Max Activating Token Index: 856

Text #6

Max Range: 3.1637. Min Range: -3.1637

Max Act: 2.9543. Min Act: -0.1700

Data Index: 9571 (Open Web Text)

Max Activating Token Index: 699

Text #7

Max Range: 3.1637. Min Range: -3.1637

Max Act: 2.9430. Min Act: -0.1700

Data Index: 4665101 (Open Web Text)

Max Activating Token Index: 606

Text #8

Max Range: 3.1637. Min Range: -3.1637

Max Act: 2.9534. Min Act: -0.1700

Data Index: 4411516 (Open Web Text)

Max Activating Token Index: 129

Text #9

Max Range: 3.1637. Min Range: -3.1637

Max Act: 2.9279. Min Act: -0.1700

Data Index: 6545872 (Open Web Text)

Max Activating Token Index: 820

Text #10

Max Range: 3.1637. Min Range: -3.1637

Max Act: 2.9188. Min Act: -0.1700

Data Index: 3503774 (Open Web Text)

Max Activating Token Index: 458

Text #11

Max Range: 3.1637. Min Range: -3.1637

Max Act: 2.9147. Min Act: -0.1700

Data Index: 1119292 (Open Web Text)

Max Activating Token Index: 252

Text #12

Max Range: 3.1637. Min Range: -3.1637

Max Act: 2.9219. Min Act: -0.1700

Data Index: 656777 (Open Web Text)

Max Activating Token Index: 730

Text #13

Max Range: 3.1637. Min Range: -3.1637

Max Act: 2.9306. Min Act: -0.1700

Data Index: 5218058 (Open Web Text)

Max Activating Token Index: 706

Text #14

Max Range: 3.1637. Min Range: -3.1637

Max Act: 2.8985. Min Act: -0.1700

Data Index: 5206512 (Open Web Text)

Max Activating Token Index: 542

Text #15

Max Range: 3.1637. Min Range: -3.1637

Max Act: 2.8769. Min Act: -0.1700

Data Index: 3657277 (Open Web Text)

Max Activating Token Index: 59

Text #16

Max Range: 3.1637. Min Range: -3.1637

Max Act: 2.8892. Min Act: -0.1700

Data Index: 6865836 (Open Web Text)

Max Activating Token Index: 198

Text #17

Max Range: 3.1637. Min Range: -3.1637

Max Act: 2.9056. Min Act: -0.1700

Data Index: 2626784 (Open Web Text)

Max Activating Token Index: 755

Text #18

Max Range: 3.1637. Min Range: -3.1637

Max Act: 2.8804. Min Act: -0.1700

Data Index: 1587190 (Open Web Text)

Max Activating Token Index: 928

Text #19

Max Range: 3.1637. Min Range: -3.1637

Max Act: 2.8599. Min Act: -0.1700

Data Index: 3472190 (Open Web Text)

Max Activating Token Index: 184