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

Dataset: Open Web Text

Neuron 915 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: 4.0083. Min Range: -4.0083

Max Act: 4.0083. Min Act: -0.1700

Data Index: 5903127 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 4.0083. Min Range: -4.0083

Max Act: 3.9492. Min Act: -0.1700

Data Index: 8048913 (Open Web Text)

Max Activating Token Index: 914

Text #2

Max Range: 4.0083. Min Range: -4.0083

Max Act: 3.9129. Min Act: -0.1700

Data Index: 5747219 (Open Web Text)

Max Activating Token Index: 669

Text #3

Max Range: 4.0083. Min Range: -4.0083

Max Act: 3.9130. Min Act: -0.1700

Data Index: 5747220 (Open Web Text)

Max Activating Token Index: 162

Text #4

Max Range: 4.0083. Min Range: -4.0083

Max Act: 3.8166. Min Act: -0.1700

Data Index: 616447 (Open Web Text)

Max Activating Token Index: 133

Text #5

Max Range: 4.0083. Min Range: -4.0083

Max Act: 3.7842. Min Act: -0.1700

Data Index: 3975505 (Open Web Text)

Max Activating Token Index: 61

Text #6

Max Range: 4.0083. Min Range: -4.0083

Max Act: 3.8066. Min Act: -0.1700

Data Index: 207728 (Open Web Text)

Max Activating Token Index: 351

Text #7

Max Range: 4.0083. Min Range: -4.0083

Max Act: 3.7413. Min Act: -0.1700

Data Index: 8253217 (Open Web Text)

Max Activating Token Index: 439

Text #8

Max Range: 4.0083. Min Range: -4.0083

Max Act: 3.7734. Min Act: -0.1700

Data Index: 3109367 (Open Web Text)

Max Activating Token Index: 915

Text #9

Max Range: 4.0083. Min Range: -4.0083

Max Act: 3.7820. Min Act: -0.1700

Data Index: 7351441 (Open Web Text)

Max Activating Token Index: 772

Text #10

Max Range: 4.0083. Min Range: -4.0083

Max Act: 3.7704. Min Act: -0.1700

Data Index: 4932563 (Open Web Text)

Max Activating Token Index: 156

Text #11

Max Range: 4.0083. Min Range: -4.0083

Max Act: 3.7700. Min Act: -0.1700

Data Index: 7149719 (Open Web Text)

Max Activating Token Index: 394

Text #12

Max Range: 4.0083. Min Range: -4.0083

Max Act: 3.7639. Min Act: -0.1700

Data Index: 857587 (Open Web Text)

Max Activating Token Index: 298

Text #13

Max Range: 4.0083. Min Range: -4.0083

Max Act: 3.7431. Min Act: -0.1700

Data Index: 2797482 (Open Web Text)

Max Activating Token Index: 745

Text #14

Max Range: 4.0083. Min Range: -4.0083

Max Act: 3.7462. Min Act: -0.1700

Data Index: 2496624 (Open Web Text)

Max Activating Token Index: 675

Text #15

Max Range: 4.0083. Min Range: -4.0083

Max Act: 3.7440. Min Act: -0.1700

Data Index: 4557791 (Open Web Text)

Max Activating Token Index: 815

Text #16

Max Range: 4.0083. Min Range: -4.0083

Max Act: 3.7406. Min Act: -0.1700

Data Index: 2966726 (Open Web Text)

Max Activating Token Index: 78

Text #17

Max Range: 4.0083. Min Range: -4.0083

Max Act: 3.7697. Min Act: -0.1700

Data Index: 2294092 (Open Web Text)

Max Activating Token Index: 13

Text #18

Max Range: 4.0083. Min Range: -4.0083

Max Act: 3.7485. Min Act: -0.1700

Data Index: 6654344 (Open Web Text)

Max Activating Token Index: 634

Text #19

Max Range: 4.0083. Min Range: -4.0083

Max Act: 3.7528. Min Act: -0.1700

Data Index: 1806671 (Open Web Text)

Max Activating Token Index: 496