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

Dataset: Open Web Text

Neuron 1410 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: 3.4087. Min Range: -3.4087

Max Act: 3.4087. Min Act: -0.1700

Data Index: 8018456 (Open Web Text)

Max Activating Token Index: 9

Text #1

Max Range: 3.4087. Min Range: -3.4087

Max Act: 3.4074. Min Act: -0.1700

Data Index: 5296598 (Open Web Text)

Max Activating Token Index: 10

Text #2

Max Range: 3.4087. Min Range: -3.4087

Max Act: 3.3899. Min Act: -0.1700

Data Index: 4178341 (Open Web Text)

Max Activating Token Index: 1010

Text #3

Max Range: 3.4087. Min Range: -3.4087

Max Act: 3.3795. Min Act: -0.1700

Data Index: 963423 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.4087. Min Range: -3.4087

Max Act: 3.3791. Min Act: -0.1700

Data Index: 1152969 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 3.4087. Min Range: -3.4087

Max Act: 3.3396. Min Act: -0.1700

Data Index: 7864398 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.4087. Min Range: -3.4087

Max Act: 3.3555. Min Act: -0.1700

Data Index: 910293 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 3.4087. Min Range: -3.4087

Max Act: 3.3441. Min Act: -0.1700

Data Index: 7480935 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 3.4087. Min Range: -3.4087

Max Act: 3.3307. Min Act: -0.1700

Data Index: 3825411 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 3.4087. Min Range: -3.4087

Max Act: 3.3465. Min Act: -0.1700

Data Index: 1331495 (Open Web Text)

Max Activating Token Index: 550

Text #10

Max Range: 3.4087. Min Range: -3.4087

Max Act: 3.3396. Min Act: -0.1700

Data Index: 7455405 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 3.4087. Min Range: -3.4087

Max Act: 3.3433. Min Act: -0.1700

Data Index: 2844318 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 3.4087. Min Range: -3.4087

Max Act: 3.3484. Min Act: -0.1700

Data Index: 6775499 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 3.4087. Min Range: -3.4087

Max Act: 3.3396. Min Act: -0.1700

Data Index: 6046272 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.4087. Min Range: -3.4087

Max Act: 3.3606. Min Act: -0.1700

Data Index: 8156640 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 3.4087. Min Range: -3.4087

Max Act: 3.3231. Min Act: -0.1700

Data Index: 7182924 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 3.4087. Min Range: -3.4087

Max Act: 3.3091. Min Act: -0.1700

Data Index: 2757888 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 3.4087. Min Range: -3.4087

Max Act: 3.3188. Min Act: -0.1700

Data Index: 6652224 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 3.4087. Min Range: -3.4087

Max Act: 3.3153. Min Act: -0.1700

Data Index: 5688911 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 3.4087. Min Range: -3.4087

Max Act: 3.2906. Min Act: -0.1700

Data Index: 232665 (Open Web Text)

Max Activating Token Index: 5