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

Dataset: Open Web Text

Neuron 2818 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: 4.3660. Min Range: -4.3660

Max Act: 4.3660. Min Act: -0.1700

Data Index: 1393974 (Open Web Text)

Max Activating Token Index: 720

Text #1

Max Range: 4.3660. Min Range: -4.3660

Max Act: 4.3132. Min Act: -0.1700

Data Index: 7582374 (Open Web Text)

Max Activating Token Index: 900

Text #2

Max Range: 4.3660. Min Range: -4.3660

Max Act: 4.2425. Min Act: -0.1700

Data Index: 2671197 (Open Web Text)

Max Activating Token Index: 933

Text #3

Max Range: 4.3660. Min Range: -4.3660

Max Act: 4.3055. Min Act: -0.1700

Data Index: 4785217 (Open Web Text)

Max Activating Token Index: 472

Text #4

Max Range: 4.3660. Min Range: -4.3660

Max Act: 4.2699. Min Act: -0.1700

Data Index: 2270921 (Open Web Text)

Max Activating Token Index: 62

Text #5

Max Range: 4.3660. Min Range: -4.3660

Max Act: 4.2913. Min Act: -0.1700

Data Index: 2068775 (Open Web Text)

Max Activating Token Index: 70

Text #6

Max Range: 4.3660. Min Range: -4.3660

Max Act: 4.2487. Min Act: -0.1700

Data Index: 5175188 (Open Web Text)

Max Activating Token Index: 170

Text #7

Max Range: 4.3660. Min Range: -4.3660

Max Act: 4.2631. Min Act: -0.1700

Data Index: 5238612 (Open Web Text)

Max Activating Token Index: 620

Text #8

Max Range: 4.3660. Min Range: -4.3660

Max Act: 4.2965. Min Act: -0.1700

Data Index: 7000324 (Open Web Text)

Max Activating Token Index: 923

Text #9

Max Range: 4.3660. Min Range: -4.3660

Max Act: 4.2920. Min Act: -0.1700

Data Index: 4667849 (Open Web Text)

Max Activating Token Index: 184

Text #10

Max Range: 4.3660. Min Range: -4.3660

Max Act: 4.2377. Min Act: -0.1700

Data Index: 3048835 (Open Web Text)

Max Activating Token Index: 32

Text #11

Max Range: 4.3660. Min Range: -4.3660

Max Act: 4.2693. Min Act: -0.1700

Data Index: 4171643 (Open Web Text)

Max Activating Token Index: 943

Text #12

Max Range: 4.3660. Min Range: -4.3660

Max Act: 4.2744. Min Act: -0.1700

Data Index: 396724 (Open Web Text)

Max Activating Token Index: 416

Text #13

Max Range: 4.3660. Min Range: -4.3660

Max Act: 4.2274. Min Act: -0.1700

Data Index: 3246777 (Open Web Text)

Max Activating Token Index: 559

Text #14

Max Range: 4.3660. Min Range: -4.3660

Max Act: 4.2805. Min Act: -0.1700

Data Index: 7618651 (Open Web Text)

Max Activating Token Index: 187

Text #15

Max Range: 4.3660. Min Range: -4.3660

Max Act: 4.2437. Min Act: -0.1700

Data Index: 5650172 (Open Web Text)

Max Activating Token Index: 228

Text #16

Max Range: 4.3660. Min Range: -4.3660

Max Act: 4.2445. Min Act: -0.1700

Data Index: 2556249 (Open Web Text)

Max Activating Token Index: 917

Text #17

Max Range: 4.3660. Min Range: -4.3660

Max Act: 4.2331. Min Act: -0.1700

Data Index: 4091187 (Open Web Text)

Max Activating Token Index: 238

Text #18

Max Range: 4.3660. Min Range: -4.3660

Max Act: 4.1891. Min Act: -0.1700

Data Index: 1407597 (Open Web Text)

Max Activating Token Index: 793

Text #19

Max Range: 4.3660. Min Range: -4.3660

Max Act: 4.2236. Min Act: -0.1700

Data Index: 5126574 (Open Web Text)

Max Activating Token Index: 73