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

Dataset: Open Web Text

Neuron 1244 in Layer 3

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: 3.6796. Min Range: -3.6796

Max Act: 3.6635. Min Act: -0.1700

Data Index: 5862025 (Open Web Text)

Max Activating Token Index: 943

Text #1

Max Range: 3.6796. Min Range: -3.6796

Max Act: 3.6540. Min Act: -0.1700

Data Index: 5899643 (Open Web Text)

Max Activating Token Index: 464

Text #2

Max Range: 3.6796. Min Range: -3.6796

Max Act: 3.6547. Min Act: -0.1700

Data Index: 6197450 (Open Web Text)

Max Activating Token Index: 740

Text #3

Max Range: 3.6796. Min Range: -3.6796

Max Act: 3.6796. Min Act: -0.1700

Data Index: 2795264 (Open Web Text)

Max Activating Token Index: 657

Text #4

Max Range: 3.6796. Min Range: -3.6796

Max Act: 3.6711. Min Act: -0.1700

Data Index: 750620 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 3.6796. Min Range: -3.6796

Max Act: 3.6392. Min Act: -0.1700

Data Index: 1531187 (Open Web Text)

Max Activating Token Index: 719

Text #6

Max Range: 3.6796. Min Range: -3.6796

Max Act: 3.6217. Min Act: -0.1700

Data Index: 909234 (Open Web Text)

Max Activating Token Index: 576

Text #7

Max Range: 3.6796. Min Range: -3.6796

Max Act: 3.6526. Min Act: -0.1700

Data Index: 2815646 (Open Web Text)

Max Activating Token Index: 882

Text #8

Max Range: 3.6796. Min Range: -3.6796

Max Act: 3.6488. Min Act: -0.1700

Data Index: 2441974 (Open Web Text)

Max Activating Token Index: 509

Text #9

Max Range: 3.6796. Min Range: -3.6796

Max Act: 3.6020. Min Act: -0.1700

Data Index: 6343643 (Open Web Text)

Max Activating Token Index: 755

Text #10

Max Range: 3.6796. Min Range: -3.6796

Max Act: 3.5997. Min Act: -0.1700

Data Index: 3085228 (Open Web Text)

Max Activating Token Index: 629

Text #11

Max Range: 3.6796. Min Range: -3.6796

Max Act: 3.6094. Min Act: -0.1700

Data Index: 3346265 (Open Web Text)

Max Activating Token Index: 749

Text #12

Max Range: 3.6796. Min Range: -3.6796

Max Act: 3.6191. Min Act: -0.1700

Data Index: 7102433 (Open Web Text)

Max Activating Token Index: 509

Text #13

Max Range: 3.6796. Min Range: -3.6796

Max Act: 3.6001. Min Act: -0.1700

Data Index: 7690843 (Open Web Text)

Max Activating Token Index: 288

Text #14

Max Range: 3.6796. Min Range: -3.6796

Max Act: 3.6119. Min Act: -0.1700

Data Index: 4476845 (Open Web Text)

Max Activating Token Index: 814

Text #15

Max Range: 3.6796. Min Range: -3.6796

Max Act: 3.5895. Min Act: -0.1700

Data Index: 1331509 (Open Web Text)

Max Activating Token Index: 773

Text #16

Max Range: 3.6796. Min Range: -3.6796

Max Act: 3.5934. Min Act: -0.1700

Data Index: 4610775 (Open Web Text)

Max Activating Token Index: 966

Text #17

Max Range: 3.6796. Min Range: -3.6796

Max Act: 3.5967. Min Act: -0.1700

Data Index: 181786 (Open Web Text)

Max Activating Token Index: 387

Text #18

Max Range: 3.6796. Min Range: -3.6796

Max Act: 3.5992. Min Act: -0.1700

Data Index: 7787280 (Open Web Text)

Max Activating Token Index: 37

Text #19

Max Range: 3.6796. Min Range: -3.6796

Max Act: 3.5956. Min Act: -0.1700

Data Index: 4664706 (Open Web Text)

Max Activating Token Index: 151