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

Dataset: Open Web Text

Neuron 1509 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: 3.4589. Min Range: -3.4589

Max Act: 3.4589. Min Act: -0.1700

Data Index: 8144383 (Open Web Text)

Max Activating Token Index: 457

Text #1

Max Range: 3.4589. Min Range: -3.4589

Max Act: 3.4374. Min Act: -0.1700

Data Index: 4205466 (Open Web Text)

Max Activating Token Index: 913

Text #2

Max Range: 3.4589. Min Range: -3.4589

Max Act: 3.4390. Min Act: -0.1700

Data Index: 2650063 (Open Web Text)

Max Activating Token Index: 227

Text #3

Max Range: 3.4589. Min Range: -3.4589

Max Act: 3.3805. Min Act: -0.1700

Data Index: 8358519 (Open Web Text)

Max Activating Token Index: 416

Text #4

Max Range: 3.4589. Min Range: -3.4589

Max Act: 3.3435. Min Act: -0.1700

Data Index: 4009521 (Open Web Text)

Max Activating Token Index: 301

Text #5

Max Range: 3.4589. Min Range: -3.4589

Max Act: 3.3301. Min Act: -0.1700

Data Index: 8435328 (Open Web Text)

Max Activating Token Index: 157

Text #6

Max Range: 3.4589. Min Range: -3.4589

Max Act: 3.3218. Min Act: -0.1700

Data Index: 8592172 (Open Web Text)

Max Activating Token Index: 939

Text #7

Max Range: 3.4589. Min Range: -3.4589

Max Act: 3.3358. Min Act: -0.1700

Data Index: 8296335 (Open Web Text)

Max Activating Token Index: 170

Text #8

Max Range: 3.4589. Min Range: -3.4589

Max Act: 3.2926. Min Act: -0.1700

Data Index: 1908197 (Open Web Text)

Max Activating Token Index: 531

Text #9

Max Range: 3.4589. Min Range: -3.4589

Max Act: 3.3149. Min Act: -0.1700

Data Index: 8731224 (Open Web Text)

Max Activating Token Index: 959

Text #10

Max Range: 3.4589. Min Range: -3.4589

Max Act: 3.2871. Min Act: -0.1700

Data Index: 6177972 (Open Web Text)

Max Activating Token Index: 494

Text #11

Max Range: 3.4589. Min Range: -3.4589

Max Act: 3.2889. Min Act: -0.1700

Data Index: 8219938 (Open Web Text)

Max Activating Token Index: 32

Text #12

Max Range: 3.4589. Min Range: -3.4589

Max Act: 3.2336. Min Act: -0.1700

Data Index: 7832244 (Open Web Text)

Max Activating Token Index: 865

Text #13

Max Range: 3.4589. Min Range: -3.4589

Max Act: 3.2416. Min Act: -0.1700

Data Index: 4150520 (Open Web Text)

Max Activating Token Index: 498

Text #14

Max Range: 3.4589. Min Range: -3.4589

Max Act: 3.2020. Min Act: -0.1700

Data Index: 2793747 (Open Web Text)

Max Activating Token Index: 984

Text #15

Max Range: 3.4589. Min Range: -3.4589

Max Act: 3.2330. Min Act: -0.1700

Data Index: 8572986 (Open Web Text)

Max Activating Token Index: 609

Text #16

Max Range: 3.4589. Min Range: -3.4589

Max Act: 3.2394. Min Act: -0.1700

Data Index: 7842150 (Open Web Text)

Max Activating Token Index: 568

Text #17

Max Range: 3.4589. Min Range: -3.4589

Max Act: 3.2457. Min Act: -0.1700

Data Index: 4707392 (Open Web Text)

Max Activating Token Index: 488

Text #18

Max Range: 3.4589. Min Range: -3.4589

Max Act: 3.2255. Min Act: -0.1700

Data Index: 3369861 (Open Web Text)

Max Activating Token Index: 43

Text #19

Max Range: 3.4589. Min Range: -3.4589

Max Act: 3.2094. Min Act: -0.1700

Data Index: 7570293 (Open Web Text)

Max Activating Token Index: 502