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

Dataset: Open Web Text

Neuron 1640 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: 4.5391. Min Range: -4.5391

Max Act: 4.5391. Min Act: -0.1700

Data Index: 2464384 (Open Web Text)

Max Activating Token Index: 74

Text #1

Max Range: 4.5391. Min Range: -4.5391

Max Act: 4.4552. Min Act: -0.1700

Data Index: 2639182 (Open Web Text)

Max Activating Token Index: 856

Text #2

Max Range: 4.5391. Min Range: -4.5391

Max Act: 4.3696. Min Act: -0.1700

Data Index: 2442961 (Open Web Text)

Max Activating Token Index: 526

Text #3

Max Range: 4.5391. Min Range: -4.5391

Max Act: 4.3328. Min Act: -0.1700

Data Index: 2217955 (Open Web Text)

Max Activating Token Index: 572

Text #4

Max Range: 4.5391. Min Range: -4.5391

Max Act: 4.3418. Min Act: -0.1700

Data Index: 6222839 (Open Web Text)

Max Activating Token Index: 408

Text #5

Max Range: 4.5391. Min Range: -4.5391

Max Act: 4.3104. Min Act: -0.1700

Data Index: 6237319 (Open Web Text)

Max Activating Token Index: 454

Text #6

Max Range: 4.5391. Min Range: -4.5391

Max Act: 4.2929. Min Act: -0.1700

Data Index: 7898971 (Open Web Text)

Max Activating Token Index: 285

Text #7

Max Range: 4.5391. Min Range: -4.5391

Max Act: 4.2464. Min Act: -0.1700

Data Index: 8661526 (Open Web Text)

Max Activating Token Index: 332

Text #8

Max Range: 4.5391. Min Range: -4.5391

Max Act: 4.2420. Min Act: -0.1700

Data Index: 2854739 (Open Web Text)

Max Activating Token Index: 426

Text #9

Max Range: 4.5391. Min Range: -4.5391

Max Act: 4.2404. Min Act: -0.1700

Data Index: 372409 (Open Web Text)

Max Activating Token Index: 518

Text #10

Max Range: 4.5391. Min Range: -4.5391

Max Act: 4.2466. Min Act: -0.1700

Data Index: 3262879 (Open Web Text)

Max Activating Token Index: 142

Text #11

Max Range: 4.5391. Min Range: -4.5391

Max Act: 4.2160. Min Act: -0.1700

Data Index: 2546036 (Open Web Text)

Max Activating Token Index: 944

Text #12

Max Range: 4.5391. Min Range: -4.5391

Max Act: 4.2407. Min Act: -0.1700

Data Index: 868919 (Open Web Text)

Max Activating Token Index: 308

Text #13

Max Range: 4.5391. Min Range: -4.5391

Max Act: 4.1612. Min Act: -0.1700

Data Index: 6116676 (Open Web Text)

Max Activating Token Index: 141

Text #14

Max Range: 4.5391. Min Range: -4.5391

Max Act: 4.2008. Min Act: -0.1700

Data Index: 694774 (Open Web Text)

Max Activating Token Index: 303

Text #15

Max Range: 4.5391. Min Range: -4.5391

Max Act: 4.1931. Min Act: -0.1700

Data Index: 2116141 (Open Web Text)

Max Activating Token Index: 481

Text #16

Max Range: 4.5391. Min Range: -4.5391

Max Act: 4.1749. Min Act: -0.1700

Data Index: 2809288 (Open Web Text)

Max Activating Token Index: 854

Text #17

Max Range: 4.5391. Min Range: -4.5391

Max Act: 4.1968. Min Act: -0.1700

Data Index: 5319534 (Open Web Text)

Max Activating Token Index: 445

Text #18

Max Range: 4.5391. Min Range: -4.5391

Max Act: 4.2099. Min Act: -0.1700

Data Index: 6439479 (Open Web Text)

Max Activating Token Index: 351

Text #19

Max Range: 4.5391. Min Range: -4.5391

Max Act: 4.2169. Min Act: -0.1700

Data Index: 2911000 (Open Web Text)

Max Activating Token Index: 234