Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2484 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3963. Min Range: -0.3963

Max Act: 0.3930. Min Act: -0.0000

Data Index: 267215 (C4 (Web Text))

Max Activating Token Index: 223

Text #1

Max Range: 0.3963. Min Range: -0.3963

Max Act: 0.3631. Min Act: -0.0000

Data Index: 4803 (C4 (Web Text))

Max Activating Token Index: 139

Text #2

Max Range: 0.3963. Min Range: -0.3963

Max Act: 0.3948. Min Act: -0.0000

Data Index: 1337172 (C4 (Web Text))

Max Activating Token Index: 29

Text #3

Max Range: 0.3963. Min Range: -0.3963

Max Act: 0.3787. Min Act: -0.0000

Data Index: 1116199 (C4 (Web Text))

Max Activating Token Index: 161

Text #4

Max Range: 0.3963. Min Range: -0.3963

Max Act: 0.3112. Min Act: -0.0000

Data Index: 420215 (C4 (Web Text))

Max Activating Token Index: 178

Text #5

Max Range: 0.3963. Min Range: -0.3963

Max Act: 0.3900. Min Act: -0.0000

Data Index: 308862 (C4 (Web Text))

Max Activating Token Index: 188

Text #6

Max Range: 0.3963. Min Range: -0.3963

Max Act: 0.3493. Min Act: -0.0000

Data Index: 36019 (C4 (Web Text))

Max Activating Token Index: 1001

Text #7

Max Range: 0.3963. Min Range: -0.3963

Max Act: 0.3635. Min Act: -0.0000

Data Index: 466825 (C4 (Web Text))

Max Activating Token Index: 378

Text #8

Max Range: 0.3963. Min Range: -0.3963

Max Act: 0.3963. Min Act: -0.0000

Data Index: 1099798 (C4 (Web Text))

Max Activating Token Index: 375

Text #9

Max Range: 0.3963. Min Range: -0.3963

Max Act: 0.3655. Min Act: -0.0000

Data Index: 825654 (C4 (Web Text))

Max Activating Token Index: 139

Text #10

Max Range: 0.3963. Min Range: -0.3963

Max Act: 0.3502. Min Act: -0.0000

Data Index: 900748 (C4 (Web Text))

Max Activating Token Index: 51

Text #11

Max Range: 0.3963. Min Range: -0.3963

Max Act: 0.3458. Min Act: -0.0000

Data Index: 1064602 (C4 (Web Text))

Max Activating Token Index: 498

Text #12

Max Range: 0.3963. Min Range: -0.3963

Max Act: 0.3123. Min Act: -0.0000

Data Index: 1151950 (C4 (Web Text))

Max Activating Token Index: 720

Text #13

Max Range: 0.3963. Min Range: -0.3963

Max Act: 0.3119. Min Act: -0.0000

Data Index: 1335349 (C4 (Web Text))

Max Activating Token Index: 629

Text #14

Max Range: 0.3963. Min Range: -0.3963

Max Act: 0.3155. Min Act: -0.0000

Data Index: 1538772 (Python Code)

Max Activating Token Index: 370

Text #15

Max Range: 0.3963. Min Range: -0.3963

Max Act: 0.2970. Min Act: -0.0000

Data Index: 1610253 (Python Code)

Max Activating Token Index: 247

Text #16

Max Range: 0.3963. Min Range: -0.3963

Max Act: 0.3318. Min Act: -0.0000

Data Index: 1444454 (Python Code)

Max Activating Token Index: 291

Text #17

Max Range: 0.3963. Min Range: -0.3963

Max Act: 0.3708. Min Act: -0.0000

Data Index: 236933 (C4 (Web Text))

Max Activating Token Index: 194

Text #18

Max Range: 0.3963. Min Range: -0.3963

Max Act: 0.3545. Min Act: -0.0000

Data Index: 1485361 (Python Code)

Max Activating Token Index: 716

Text #19

Max Range: 0.3963. Min Range: -0.3963

Max Act: 0.3288. Min Act: -0.0000

Data Index: 1447111 (Python Code)

Max Activating Token Index: 926