Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 281 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.4247. Min Act: -0.0001

Data Index: 550882 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.4061. Min Act: -0.0001

Data Index: 453174 (C4 (Web Text))

Max Activating Token Index: 894

Text #2

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.3912. Min Act: -0.0001

Data Index: 402685 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.4011. Min Act: -0.0001

Data Index: 323711 (C4 (Web Text))

Max Activating Token Index: 348

Text #4

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.4037. Min Act: -0.0001

Data Index: 1134001 (C4 (Web Text))

Max Activating Token Index: 903

Text #5

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.3947. Min Act: -0.0001

Data Index: 180887 (C4 (Web Text))

Max Activating Token Index: 102

Text #6

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.3864. Min Act: -0.0001

Data Index: 561668 (C4 (Web Text))

Max Activating Token Index: 557

Text #7

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.3551. Min Act: -0.0001

Data Index: 250195 (C4 (Web Text))

Max Activating Token Index: 330

Text #8

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.3895. Min Act: -0.0001

Data Index: 1106552 (C4 (Web Text))

Max Activating Token Index: 536

Text #9

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.3890. Min Act: -0.0001

Data Index: 811001 (C4 (Web Text))

Max Activating Token Index: 741

Text #10

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.3649. Min Act: -0.0001

Data Index: 913804 (C4 (Web Text))

Max Activating Token Index: 326

Text #11

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.3730. Min Act: -0.0001

Data Index: 1173216 (C4 (Web Text))

Max Activating Token Index: 686

Text #12

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.3677. Min Act: -0.0001

Data Index: 259919 (C4 (Web Text))

Max Activating Token Index: 50

Text #13

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.3753. Min Act: -0.0001

Data Index: 95695 (C4 (Web Text))

Max Activating Token Index: 325

Text #14

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.3600. Min Act: -0.0001

Data Index: 1128378 (C4 (Web Text))

Max Activating Token Index: 34

Text #15

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.3534. Min Act: -0.0001

Data Index: 1098418 (C4 (Web Text))

Max Activating Token Index: 761

Text #16

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.3612. Min Act: -0.0001

Data Index: 839177 (C4 (Web Text))

Max Activating Token Index: 298

Text #17

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.3448. Min Act: -0.0001

Data Index: 1318138 (C4 (Web Text))

Max Activating Token Index: 453

Text #18

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.3314. Min Act: -0.0001

Data Index: 1058291 (C4 (Web Text))

Max Activating Token Index: 23

Text #19

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.3424. Min Act: -0.0001

Data Index: 576956 (C4 (Web Text))

Max Activating Token Index: 253