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

Dataset: Open Web Text

Neuron 225 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: 2.9097. Min Range: -2.9097

Max Act: 2.9097. Min Act: -0.1700

Data Index: 1942449 (Open Web Text)

Max Activating Token Index: 266

Text #1

Max Range: 2.9097. Min Range: -2.9097

Max Act: 2.8019. Min Act: -0.1700

Data Index: 629536 (Open Web Text)

Max Activating Token Index: 937

Text #2

Max Range: 2.9097. Min Range: -2.9097

Max Act: 2.8235. Min Act: -0.1700

Data Index: 1200223 (Open Web Text)

Max Activating Token Index: 196

Text #3

Max Range: 2.9097. Min Range: -2.9097

Max Act: 2.8034. Min Act: -0.1700

Data Index: 5984599 (Open Web Text)

Max Activating Token Index: 140

Text #4

Max Range: 2.9097. Min Range: -2.9097

Max Act: 2.7782. Min Act: -0.1700

Data Index: 7877482 (Open Web Text)

Max Activating Token Index: 589

Text #5

Max Range: 2.9097. Min Range: -2.9097

Max Act: 2.7886. Min Act: -0.1700

Data Index: 5127594 (Open Web Text)

Max Activating Token Index: 820

Text #6

Max Range: 2.9097. Min Range: -2.9097

Max Act: 2.7941. Min Act: -0.1700

Data Index: 4513747 (Open Web Text)

Max Activating Token Index: 702

Text #7

Max Range: 2.9097. Min Range: -2.9097

Max Act: 2.8107. Min Act: -0.1700

Data Index: 2464809 (Open Web Text)

Max Activating Token Index: 479

Text #8

Max Range: 2.9097. Min Range: -2.9097

Max Act: 2.7958. Min Act: -0.1700

Data Index: 8153658 (Open Web Text)

Max Activating Token Index: 610

Text #9

Max Range: 2.9097. Min Range: -2.9097

Max Act: 2.7637. Min Act: -0.1700

Data Index: 8749890 (Open Web Text)

Max Activating Token Index: 983

Text #10

Max Range: 2.9097. Min Range: -2.9097

Max Act: 2.7622. Min Act: -0.1700

Data Index: 8125624 (Open Web Text)

Max Activating Token Index: 697

Text #11

Max Range: 2.9097. Min Range: -2.9097

Max Act: 2.7510. Min Act: -0.1700

Data Index: 1701061 (Open Web Text)

Max Activating Token Index: 370

Text #12

Max Range: 2.9097. Min Range: -2.9097

Max Act: 2.7341. Min Act: -0.1700

Data Index: 2092536 (Open Web Text)

Max Activating Token Index: 562

Text #13

Max Range: 2.9097. Min Range: -2.9097

Max Act: 2.7476. Min Act: -0.1700

Data Index: 7148546 (Open Web Text)

Max Activating Token Index: 1018

Text #14

Max Range: 2.9097. Min Range: -2.9097

Max Act: 2.7578. Min Act: -0.1700

Data Index: 8764312 (Open Web Text)

Max Activating Token Index: 758

Text #15

Max Range: 2.9097. Min Range: -2.9097

Max Act: 2.7494. Min Act: -0.1700

Data Index: 7742999 (Open Web Text)

Max Activating Token Index: 427

Text #16

Max Range: 2.9097. Min Range: -2.9097

Max Act: 2.7570. Min Act: -0.1700

Data Index: 7420628 (Open Web Text)

Max Activating Token Index: 716

Text #17

Max Range: 2.9097. Min Range: -2.9097

Max Act: 2.7212. Min Act: -0.1700

Data Index: 4123204 (Open Web Text)

Max Activating Token Index: 188

Text #18

Max Range: 2.9097. Min Range: -2.9097

Max Act: 2.7327. Min Act: -0.1700

Data Index: 6857022 (Open Web Text)

Max Activating Token Index: 458

Text #19

Max Range: 2.9097. Min Range: -2.9097

Max Act: 2.7303. Min Act: -0.1700

Data Index: 4598931 (Open Web Text)

Max Activating Token Index: 47