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

Dataset: Open Web Text

Neuron 2516 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: 3.8248. Min Range: -3.8248

Max Act: 3.8248. Min Act: -0.1700

Data Index: 6668969 (Open Web Text)

Max Activating Token Index: 648

Text #1

Max Range: 3.8248. Min Range: -3.8248

Max Act: 3.7946. Min Act: -0.1700

Data Index: 8320704 (Open Web Text)

Max Activating Token Index: 637

Text #2

Max Range: 3.8248. Min Range: -3.8248

Max Act: 3.7901. Min Act: -0.1700

Data Index: 5325629 (Open Web Text)

Max Activating Token Index: 834

Text #3

Max Range: 3.8248. Min Range: -3.8248

Max Act: 3.7539. Min Act: -0.1700

Data Index: 8194266 (Open Web Text)

Max Activating Token Index: 20

Text #4

Max Range: 3.8248. Min Range: -3.8248

Max Act: 3.7531. Min Act: -0.1700

Data Index: 803342 (Open Web Text)

Max Activating Token Index: 216

Text #5

Max Range: 3.8248. Min Range: -3.8248

Max Act: 3.7282. Min Act: -0.1700

Data Index: 1085088 (Open Web Text)

Max Activating Token Index: 206

Text #6

Max Range: 3.8248. Min Range: -3.8248

Max Act: 3.6755. Min Act: -0.1700

Data Index: 1310387 (Open Web Text)

Max Activating Token Index: 993

Text #7

Max Range: 3.8248. Min Range: -3.8248

Max Act: 3.7236. Min Act: -0.1700

Data Index: 1670356 (Open Web Text)

Max Activating Token Index: 472

Text #8

Max Range: 3.8248. Min Range: -3.8248

Max Act: 3.6533. Min Act: -0.1700

Data Index: 6800806 (Open Web Text)

Max Activating Token Index: 27

Text #9

Max Range: 3.8248. Min Range: -3.8248

Max Act: 3.6425. Min Act: -0.1700

Data Index: 1119809 (Open Web Text)

Max Activating Token Index: 647

Text #10

Max Range: 3.8248. Min Range: -3.8248

Max Act: 3.6456. Min Act: -0.1700

Data Index: 5179175 (Open Web Text)

Max Activating Token Index: 262

Text #11

Max Range: 3.8248. Min Range: -3.8248

Max Act: 3.6384. Min Act: -0.1700

Data Index: 8486318 (Open Web Text)

Max Activating Token Index: 178

Text #12

Max Range: 3.8248. Min Range: -3.8248

Max Act: 3.6576. Min Act: -0.1700

Data Index: 3865996 (Open Web Text)

Max Activating Token Index: 647

Text #13

Max Range: 3.8248. Min Range: -3.8248

Max Act: 3.6064. Min Act: -0.1700

Data Index: 6949130 (Open Web Text)

Max Activating Token Index: 783

Text #14

Max Range: 3.8248. Min Range: -3.8248

Max Act: 3.6314. Min Act: -0.1700

Data Index: 7563361 (Open Web Text)

Max Activating Token Index: 442

Text #15

Max Range: 3.8248. Min Range: -3.8248

Max Act: 3.5942. Min Act: -0.1700

Data Index: 7944541 (Open Web Text)

Max Activating Token Index: 746

Text #16

Max Range: 3.8248. Min Range: -3.8248

Max Act: 3.6130. Min Act: -0.1700

Data Index: 7972233 (Open Web Text)

Max Activating Token Index: 338

Text #17

Max Range: 3.8248. Min Range: -3.8248

Max Act: 3.5881. Min Act: -0.1700

Data Index: 3590553 (Open Web Text)

Max Activating Token Index: 602

Text #18

Max Range: 3.8248. Min Range: -3.8248

Max Act: 3.5958. Min Act: -0.1700

Data Index: 1498663 (Open Web Text)

Max Activating Token Index: 947

Text #19

Max Range: 3.8248. Min Range: -3.8248

Max Act: 3.6121. Min Act: -0.1700

Data Index: 8304967 (Open Web Text)

Max Activating Token Index: 917