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

Dataset: Open Web Text

Neuron 2393 in Layer 6

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: 4.0964. Min Range: -4.0964

Max Act: 4.0964. Min Act: -0.1700

Data Index: 3608276 (Open Web Text)

Max Activating Token Index: 677

Text #1

Max Range: 4.0964. Min Range: -4.0964

Max Act: 4.0570. Min Act: -0.1700

Data Index: 5218892 (Open Web Text)

Max Activating Token Index: 828

Text #2

Max Range: 4.0964. Min Range: -4.0964

Max Act: 3.9421. Min Act: -0.1700

Data Index: 597070 (Open Web Text)

Max Activating Token Index: 924

Text #3

Max Range: 4.0964. Min Range: -4.0964

Max Act: 3.9549. Min Act: -0.1700

Data Index: 171000 (Open Web Text)

Max Activating Token Index: 423

Text #4

Max Range: 4.0964. Min Range: -4.0964

Max Act: 3.9498. Min Act: -0.1700

Data Index: 3779500 (Open Web Text)

Max Activating Token Index: 290

Text #5

Max Range: 4.0964. Min Range: -4.0964

Max Act: 3.9419. Min Act: -0.1700

Data Index: 4400501 (Open Web Text)

Max Activating Token Index: 502

Text #6

Max Range: 4.0964. Min Range: -4.0964

Max Act: 3.8918. Min Act: -0.1700

Data Index: 1581055 (Open Web Text)

Max Activating Token Index: 394

Text #7

Max Range: 4.0964. Min Range: -4.0964

Max Act: 3.9289. Min Act: -0.1700

Data Index: 3062117 (Open Web Text)

Max Activating Token Index: 1018

Text #8

Max Range: 4.0964. Min Range: -4.0964

Max Act: 3.9352. Min Act: -0.1700

Data Index: 5294858 (Open Web Text)

Max Activating Token Index: 261

Text #9

Max Range: 4.0964. Min Range: -4.0964

Max Act: 3.9014. Min Act: -0.1700

Data Index: 6958471 (Open Web Text)

Max Activating Token Index: 536

Text #10

Max Range: 4.0964. Min Range: -4.0964

Max Act: 3.8952. Min Act: -0.1700

Data Index: 954286 (Open Web Text)

Max Activating Token Index: 993

Text #11

Max Range: 4.0964. Min Range: -4.0964

Max Act: 3.8797. Min Act: -0.1700

Data Index: 3543963 (Open Web Text)

Max Activating Token Index: 422

Text #12

Max Range: 4.0964. Min Range: -4.0964

Max Act: 3.8536. Min Act: -0.1700

Data Index: 3905993 (Open Web Text)

Max Activating Token Index: 133

Text #13

Max Range: 4.0964. Min Range: -4.0964

Max Act: 3.8567. Min Act: -0.1700

Data Index: 3774214 (Open Web Text)

Max Activating Token Index: 414

Text #14

Max Range: 4.0964. Min Range: -4.0964

Max Act: 3.8508. Min Act: -0.1700

Data Index: 4325023 (Open Web Text)

Max Activating Token Index: 427

Text #15

Max Range: 4.0964. Min Range: -4.0964

Max Act: 3.8288. Min Act: -0.1700

Data Index: 6618943 (Open Web Text)

Max Activating Token Index: 237

Text #16

Max Range: 4.0964. Min Range: -4.0964

Max Act: 3.8061. Min Act: -0.1700

Data Index: 7964382 (Open Web Text)

Max Activating Token Index: 466

Text #17

Max Range: 4.0964. Min Range: -4.0964

Max Act: 3.8225. Min Act: -0.1700

Data Index: 160367 (Open Web Text)

Max Activating Token Index: 661

Text #18

Max Range: 4.0964. Min Range: -4.0964

Max Act: 3.8148. Min Act: -0.1700

Data Index: 5440182 (Open Web Text)

Max Activating Token Index: 87

Text #19

Max Range: 4.0964. Min Range: -4.0964

Max Act: 3.8131. Min Act: -0.1700

Data Index: 6955598 (Open Web Text)

Max Activating Token Index: 931