Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5282 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.4542. Min Act: -0.0001

Data Index: 365692 (C4 (Web Text))

Max Activating Token Index: 649

Text #1

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.4403. Min Act: -0.0001

Data Index: 673854 (C4 (Web Text))

Max Activating Token Index: 12

Text #2

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.4383. Min Act: -0.0001

Data Index: 1279162 (C4 (Web Text))

Max Activating Token Index: 68

Text #3

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.4337. Min Act: -0.0002

Data Index: 273361 (C4 (Web Text))

Max Activating Token Index: 885

Text #4

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.4293. Min Act: -0.0002

Data Index: 698517 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.4262. Min Act: -0.0001

Data Index: 469549 (C4 (Web Text))

Max Activating Token Index: 391

Text #6

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.4209. Min Act: -0.0001

Data Index: 521855 (C4 (Web Text))

Max Activating Token Index: 627

Text #7

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.4192. Min Act: -0.0001

Data Index: 1001132 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.4144. Min Act: -0.0002

Data Index: 879141 (C4 (Web Text))

Max Activating Token Index: 100

Text #9

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.4074. Min Act: -0.0001

Data Index: 1101925 (C4 (Web Text))

Max Activating Token Index: 910

Text #10

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.4094. Min Act: -0.0001

Data Index: 1078804 (C4 (Web Text))

Max Activating Token Index: 123

Text #11

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3921. Min Act: -0.0001

Data Index: 1309502 (C4 (Web Text))

Max Activating Token Index: 18

Text #12

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3988. Min Act: -0.0001

Data Index: 537106 (C4 (Web Text))

Max Activating Token Index: 611

Text #13

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.4014. Min Act: -0.0001

Data Index: 903940 (C4 (Web Text))

Max Activating Token Index: 377

Text #14

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.4038. Min Act: -0.0001

Data Index: 986374 (C4 (Web Text))

Max Activating Token Index: 404

Text #15

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.4036. Min Act: -0.0001

Data Index: 952920 (C4 (Web Text))

Max Activating Token Index: 952

Text #16

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3954. Min Act: -0.0001

Data Index: 100006 (C4 (Web Text))

Max Activating Token Index: 44

Text #17

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3890. Min Act: -0.0001

Data Index: 65811 (C4 (Web Text))

Max Activating Token Index: 815

Text #18

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3815. Min Act: -0.0001

Data Index: 709717 (C4 (Web Text))

Max Activating Token Index: 225

Text #19

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3862. Min Act: -0.0001

Data Index: 591073 (C4 (Web Text))

Max Activating Token Index: 655