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

Dataset: Open Web Text

Neuron 994 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: 3.7961. Min Range: -3.7961

Max Act: 3.7961. Min Act: -0.1700

Data Index: 790104 (Open Web Text)

Max Activating Token Index: 653

Text #1

Max Range: 3.7961. Min Range: -3.7961

Max Act: 3.7758. Min Act: -0.1700

Data Index: 4830141 (Open Web Text)

Max Activating Token Index: 612

Text #2

Max Range: 3.7961. Min Range: -3.7961

Max Act: 3.7464. Min Act: -0.1700

Data Index: 1706994 (Open Web Text)

Max Activating Token Index: 454

Text #3

Max Range: 3.7961. Min Range: -3.7961

Max Act: 3.7516. Min Act: -0.1700

Data Index: 1725146 (Open Web Text)

Max Activating Token Index: 630

Text #4

Max Range: 3.7961. Min Range: -3.7961

Max Act: 3.7203. Min Act: -0.1700

Data Index: 4074179 (Open Web Text)

Max Activating Token Index: 394

Text #5

Max Range: 3.7961. Min Range: -3.7961

Max Act: 3.7212. Min Act: -0.1700

Data Index: 2416618 (Open Web Text)

Max Activating Token Index: 667

Text #6

Max Range: 3.7961. Min Range: -3.7961

Max Act: 3.7320. Min Act: -0.1700

Data Index: 3796090 (Open Web Text)

Max Activating Token Index: 39

Text #7

Max Range: 3.7961. Min Range: -3.7961

Max Act: 3.7450. Min Act: -0.1700

Data Index: 4728139 (Open Web Text)

Max Activating Token Index: 446

Text #8

Max Range: 3.7961. Min Range: -3.7961

Max Act: 3.6898. Min Act: -0.1700

Data Index: 5847254 (Open Web Text)

Max Activating Token Index: 457

Text #9

Max Range: 3.7961. Min Range: -3.7961

Max Act: 3.7129. Min Act: -0.1700

Data Index: 5072711 (Open Web Text)

Max Activating Token Index: 14

Text #10

Max Range: 3.7961. Min Range: -3.7961

Max Act: 3.6956. Min Act: -0.1700

Data Index: 5099998 (Open Web Text)

Max Activating Token Index: 465

Text #11

Max Range: 3.7961. Min Range: -3.7961

Max Act: 3.7001. Min Act: -0.1700

Data Index: 8212244 (Open Web Text)

Max Activating Token Index: 598

Text #12

Max Range: 3.7961. Min Range: -3.7961

Max Act: 3.6862. Min Act: -0.1700

Data Index: 3323616 (Open Web Text)

Max Activating Token Index: 850

Text #13

Max Range: 3.7961. Min Range: -3.7961

Max Act: 3.6947. Min Act: -0.1700

Data Index: 4097110 (Open Web Text)

Max Activating Token Index: 191

Text #14

Max Range: 3.7961. Min Range: -3.7961

Max Act: 3.7094. Min Act: -0.1700

Data Index: 1552182 (Open Web Text)

Max Activating Token Index: 554

Text #15

Max Range: 3.7961. Min Range: -3.7961

Max Act: 3.6796. Min Act: -0.1700

Data Index: 6749128 (Open Web Text)

Max Activating Token Index: 561

Text #16

Max Range: 3.7961. Min Range: -3.7961

Max Act: 3.6751. Min Act: -0.1700

Data Index: 6800645 (Open Web Text)

Max Activating Token Index: 31

Text #17

Max Range: 3.7961. Min Range: -3.7961

Max Act: 3.6684. Min Act: -0.1700

Data Index: 7141387 (Open Web Text)

Max Activating Token Index: 355

Text #18

Max Range: 3.7961. Min Range: -3.7961

Max Act: 3.6763. Min Act: -0.1700

Data Index: 7719148 (Open Web Text)

Max Activating Token Index: 872

Text #19

Max Range: 3.7961. Min Range: -3.7961

Max Act: 3.6924. Min Act: -0.1700

Data Index: 7924192 (Open Web Text)

Max Activating Token Index: 223