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

Dataset: Open Web Text

Neuron 2308 in Layer 3

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: 4.5942. Min Range: -4.5942

Max Act: 4.5942. Min Act: -0.1700

Data Index: 2293859 (Open Web Text)

Max Activating Token Index: 508

Text #1

Max Range: 4.5942. Min Range: -4.5942

Max Act: 4.4122. Min Act: -0.1700

Data Index: 6342838 (Open Web Text)

Max Activating Token Index: 386

Text #2

Max Range: 4.5942. Min Range: -4.5942

Max Act: 4.2601. Min Act: -0.1700

Data Index: 3744744 (Open Web Text)

Max Activating Token Index: 621

Text #3

Max Range: 4.5942. Min Range: -4.5942

Max Act: 4.3157. Min Act: -0.1700

Data Index: 8680979 (Open Web Text)

Max Activating Token Index: 382

Text #4

Max Range: 4.5942. Min Range: -4.5942

Max Act: 4.3245. Min Act: -0.1700

Data Index: 6951134 (Open Web Text)

Max Activating Token Index: 541

Text #5

Max Range: 4.5942. Min Range: -4.5942

Max Act: 4.2677. Min Act: -0.1700

Data Index: 705249 (Open Web Text)

Max Activating Token Index: 820

Text #6

Max Range: 4.5942. Min Range: -4.5942

Max Act: 4.2695. Min Act: -0.1700

Data Index: 4662891 (Open Web Text)

Max Activating Token Index: 429

Text #7

Max Range: 4.5942. Min Range: -4.5942

Max Act: 4.2298. Min Act: -0.1700

Data Index: 8688347 (Open Web Text)

Max Activating Token Index: 773

Text #8

Max Range: 4.5942. Min Range: -4.5942

Max Act: 4.2545. Min Act: -0.1700

Data Index: 4036649 (Open Web Text)

Max Activating Token Index: 513

Text #9

Max Range: 4.5942. Min Range: -4.5942

Max Act: 4.2943. Min Act: -0.1700

Data Index: 8394073 (Open Web Text)

Max Activating Token Index: 429

Text #10

Max Range: 4.5942. Min Range: -4.5942

Max Act: 4.2380. Min Act: -0.1700

Data Index: 4508735 (Open Web Text)

Max Activating Token Index: 539

Text #11

Max Range: 4.5942. Min Range: -4.5942

Max Act: 4.1981. Min Act: -0.1700

Data Index: 2355738 (Open Web Text)

Max Activating Token Index: 918

Text #12

Max Range: 4.5942. Min Range: -4.5942

Max Act: 4.2439. Min Act: -0.1700

Data Index: 265708 (Open Web Text)

Max Activating Token Index: 860

Text #13

Max Range: 4.5942. Min Range: -4.5942

Max Act: 4.2384. Min Act: -0.1700

Data Index: 4514316 (Open Web Text)

Max Activating Token Index: 514

Text #14

Max Range: 4.5942. Min Range: -4.5942

Max Act: 4.2029. Min Act: -0.1700

Data Index: 4672901 (Open Web Text)

Max Activating Token Index: 643

Text #15

Max Range: 4.5942. Min Range: -4.5942

Max Act: 4.2499. Min Act: -0.1700

Data Index: 4780272 (Open Web Text)

Max Activating Token Index: 84

Text #16

Max Range: 4.5942. Min Range: -4.5942

Max Act: 4.2531. Min Act: -0.1700

Data Index: 4906096 (Open Web Text)

Max Activating Token Index: 97

Text #17

Max Range: 4.5942. Min Range: -4.5942

Max Act: 4.2956. Min Act: -0.1700

Data Index: 5215511 (Open Web Text)

Max Activating Token Index: 222

Text #18

Max Range: 4.5942. Min Range: -4.5942

Max Act: 4.2330. Min Act: -0.1700

Data Index: 5267228 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 4.5942. Min Range: -4.5942

Max Act: 4.2638. Min Act: -0.1700

Data Index: 5904021 (Open Web Text)

Max Activating Token Index: 692