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

Dataset: Open Web Text

Neuron 1119 in Layer 4

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: 5.6481. Min Range: -5.6481

Max Act: 5.6481. Min Act: -0.1700

Data Index: 8266237 (Open Web Text)

Max Activating Token Index: 575

Text #1

Max Range: 5.6481. Min Range: -5.6481

Max Act: 5.6091. Min Act: -0.1700

Data Index: 890821 (Open Web Text)

Max Activating Token Index: 850

Text #2

Max Range: 5.6481. Min Range: -5.6481

Max Act: 5.4971. Min Act: -0.1700

Data Index: 4311319 (Open Web Text)

Max Activating Token Index: 410

Text #3

Max Range: 5.6481. Min Range: -5.6481

Max Act: 5.4758. Min Act: -0.1700

Data Index: 6457287 (Open Web Text)

Max Activating Token Index: 1004

Text #4

Max Range: 5.6481. Min Range: -5.6481

Max Act: 5.4159. Min Act: -0.1700

Data Index: 7636884 (Open Web Text)

Max Activating Token Index: 589

Text #5

Max Range: 5.6481. Min Range: -5.6481

Max Act: 5.4414. Min Act: -0.1700

Data Index: 7683404 (Open Web Text)

Max Activating Token Index: 590

Text #6

Max Range: 5.6481. Min Range: -5.6481

Max Act: 5.3864. Min Act: -0.1700

Data Index: 6124077 (Open Web Text)

Max Activating Token Index: 45

Text #7

Max Range: 5.6481. Min Range: -5.6481

Max Act: 5.3590. Min Act: -0.1700

Data Index: 5601089 (Open Web Text)

Max Activating Token Index: 86

Text #8

Max Range: 5.6481. Min Range: -5.6481

Max Act: 5.3081. Min Act: -0.1700

Data Index: 2843827 (Open Web Text)

Max Activating Token Index: 943

Text #9

Max Range: 5.6481. Min Range: -5.6481

Max Act: 5.3735. Min Act: -0.1700

Data Index: 59449 (Open Web Text)

Max Activating Token Index: 146

Text #10

Max Range: 5.6481. Min Range: -5.6481

Max Act: 5.3037. Min Act: -0.1700

Data Index: 8253826 (Open Web Text)

Max Activating Token Index: 163

Text #11

Max Range: 5.6481. Min Range: -5.6481

Max Act: 5.3516. Min Act: -0.1700

Data Index: 6865983 (Open Web Text)

Max Activating Token Index: 224

Text #12

Max Range: 5.6481. Min Range: -5.6481

Max Act: 5.3185. Min Act: -0.1700

Data Index: 5229720 (Open Web Text)

Max Activating Token Index: 642

Text #13

Max Range: 5.6481. Min Range: -5.6481

Max Act: 5.3208. Min Act: -0.1700

Data Index: 3309985 (Open Web Text)

Max Activating Token Index: 884

Text #14

Max Range: 5.6481. Min Range: -5.6481

Max Act: 5.3266. Min Act: -0.1700

Data Index: 8325523 (Open Web Text)

Max Activating Token Index: 253

Text #15

Max Range: 5.6481. Min Range: -5.6481

Max Act: 5.3069. Min Act: -0.1700

Data Index: 87183 (Open Web Text)

Max Activating Token Index: 382

Text #16

Max Range: 5.6481. Min Range: -5.6481

Max Act: 5.2372. Min Act: -0.1700

Data Index: 3067328 (Open Web Text)

Max Activating Token Index: 457

Text #17

Max Range: 5.6481. Min Range: -5.6481

Max Act: 5.2619. Min Act: -0.1700

Data Index: 3312808 (Open Web Text)

Max Activating Token Index: 719

Text #18

Max Range: 5.6481. Min Range: -5.6481

Max Act: 5.2374. Min Act: -0.1700

Data Index: 3035767 (Open Web Text)

Max Activating Token Index: 414

Text #19

Max Range: 5.6481. Min Range: -5.6481

Max Act: 5.2323. Min Act: -0.1700

Data Index: 3659493 (Open Web Text)

Max Activating Token Index: 56