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

Dataset: Open Web Text

Neuron 411 in Layer 0

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: 4.3902. Min Range: -4.3902

Max Act: 4.3902. Min Act: -0.1700

Data Index: 2519877 (Open Web Text)

Max Activating Token Index: 14

Text #1

Max Range: 4.3902. Min Range: -4.3902

Max Act: 4.3661. Min Act: -0.1700

Data Index: 8067253 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 4.3902. Min Range: -4.3902

Max Act: 4.3416. Min Act: -0.1700

Data Index: 8215358 (Open Web Text)

Max Activating Token Index: 183

Text #3

Max Range: 4.3902. Min Range: -4.3902

Max Act: 4.3004. Min Act: -0.1700

Data Index: 4177638 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 4.3902. Min Range: -4.3902

Max Act: 4.2878. Min Act: -0.1700

Data Index: 1653778 (Open Web Text)

Max Activating Token Index: 11

Text #5

Max Range: 4.3902. Min Range: -4.3902

Max Act: 4.2258. Min Act: -0.1700

Data Index: 5146184 (Open Web Text)

Max Activating Token Index: 286

Text #6

Max Range: 4.3902. Min Range: -4.3902

Max Act: 4.2479. Min Act: -0.1700

Data Index: 1423672 (Open Web Text)

Max Activating Token Index: 52

Text #7

Max Range: 4.3902. Min Range: -4.3902

Max Act: 4.2478. Min Act: -0.1700

Data Index: 5026705 (Open Web Text)

Max Activating Token Index: 397

Text #8

Max Range: 4.3902. Min Range: -4.3902

Max Act: 4.2461. Min Act: -0.1700

Data Index: 5714711 (Open Web Text)

Max Activating Token Index: 791

Text #9

Max Range: 4.3902. Min Range: -4.3902

Max Act: 4.2382. Min Act: -0.1700

Data Index: 4672621 (Open Web Text)

Max Activating Token Index: 101

Text #10

Max Range: 4.3902. Min Range: -4.3902

Max Act: 4.1986. Min Act: -0.1700

Data Index: 4719089 (Open Web Text)

Max Activating Token Index: 255

Text #11

Max Range: 4.3902. Min Range: -4.3902

Max Act: 4.1998. Min Act: -0.1700

Data Index: 1067029 (Open Web Text)

Max Activating Token Index: 49

Text #12

Max Range: 4.3902. Min Range: -4.3902

Max Act: 4.1932. Min Act: -0.1700

Data Index: 4987835 (Open Web Text)

Max Activating Token Index: 23

Text #13

Max Range: 4.3902. Min Range: -4.3902

Max Act: 4.1956. Min Act: -0.1700

Data Index: 3070410 (Open Web Text)

Max Activating Token Index: 527

Text #14

Max Range: 4.3902. Min Range: -4.3902

Max Act: 4.1865. Min Act: -0.1700

Data Index: 6839010 (Open Web Text)

Max Activating Token Index: 363

Text #15

Max Range: 4.3902. Min Range: -4.3902

Max Act: 4.2040. Min Act: -0.1700

Data Index: 3106678 (Open Web Text)

Max Activating Token Index: 13

Text #16

Max Range: 4.3902. Min Range: -4.3902

Max Act: 4.2047. Min Act: -0.1700

Data Index: 792459 (Open Web Text)

Max Activating Token Index: 683

Text #17

Max Range: 4.3902. Min Range: -4.3902

Max Act: 4.1708. Min Act: -0.1700

Data Index: 924432 (Open Web Text)

Max Activating Token Index: 460

Text #18

Max Range: 4.3902. Min Range: -4.3902

Max Act: 4.1841. Min Act: -0.1700

Data Index: 3055390 (Open Web Text)

Max Activating Token Index: 9

Text #19

Max Range: 4.3902. Min Range: -4.3902

Max Act: 4.1656. Min Act: -0.1700

Data Index: 5028721 (Open Web Text)

Max Activating Token Index: 10