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

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

Neuron 1133 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3431. Min Range: -0.3431

Max Act: 0.3431. Min Act: -0.0001

Data Index: 80838 (C4 (Web Text))

Max Activating Token Index: 92

Text #1

Max Range: 0.3431. Min Range: -0.3431

Max Act: 0.3384. Min Act: -0.0001

Data Index: 102877 (C4 (Web Text))

Max Activating Token Index: 999

Text #2

Max Range: 0.3431. Min Range: -0.3431

Max Act: 0.3299. Min Act: -0.0001

Data Index: 781583 (C4 (Web Text))

Max Activating Token Index: 399

Text #3

Max Range: 0.3431. Min Range: -0.3431

Max Act: 0.3239. Min Act: -0.0001

Data Index: 134585 (C4 (Web Text))

Max Activating Token Index: 507

Text #4

Max Range: 0.3431. Min Range: -0.3431

Max Act: 0.3233. Min Act: -0.0001

Data Index: 635326 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 0.3431. Min Range: -0.3431

Max Act: 0.3225. Min Act: -0.0001

Data Index: 1118619 (C4 (Web Text))

Max Activating Token Index: 426

Text #6

Max Range: 0.3431. Min Range: -0.3431

Max Act: 0.3147. Min Act: -0.0001

Data Index: 1158680 (C4 (Web Text))

Max Activating Token Index: 401

Text #7

Max Range: 0.3431. Min Range: -0.3431

Max Act: 0.3009. Min Act: -0.0001

Data Index: 1184328 (C4 (Web Text))

Max Activating Token Index: 1017

Text #8

Max Range: 0.3431. Min Range: -0.3431

Max Act: 0.3007. Min Act: -0.0001

Data Index: 1208218 (C4 (Web Text))

Max Activating Token Index: 404

Text #9

Max Range: 0.3431. Min Range: -0.3431

Max Act: 0.3115. Min Act: -0.0001

Data Index: 6964 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 0.3431. Min Range: -0.3431

Max Act: 0.3091. Min Act: -0.0001

Data Index: 299759 (C4 (Web Text))

Max Activating Token Index: 971

Text #11

Max Range: 0.3431. Min Range: -0.3431

Max Act: 0.3087. Min Act: -0.0001

Data Index: 60212 (C4 (Web Text))

Max Activating Token Index: 148

Text #12

Max Range: 0.3431. Min Range: -0.3431

Max Act: 0.3109. Min Act: -0.0001

Data Index: 1062732 (C4 (Web Text))

Max Activating Token Index: 931

Text #13

Max Range: 0.3431. Min Range: -0.3431

Max Act: 0.3079. Min Act: -0.0001

Data Index: 1101132 (C4 (Web Text))

Max Activating Token Index: 459

Text #14

Max Range: 0.3431. Min Range: -0.3431

Max Act: 0.2972. Min Act: -0.0001

Data Index: 975871 (C4 (Web Text))

Max Activating Token Index: 73

Text #15

Max Range: 0.3431. Min Range: -0.3431

Max Act: 0.2917. Min Act: -0.0001

Data Index: 859668 (C4 (Web Text))

Max Activating Token Index: 516

Text #16

Max Range: 0.3431. Min Range: -0.3431

Max Act: 0.3104. Min Act: -0.0001

Data Index: 418701 (C4 (Web Text))

Max Activating Token Index: 1021

Text #17

Max Range: 0.3431. Min Range: -0.3431

Max Act: 0.2962. Min Act: -0.0001

Data Index: 222684 (C4 (Web Text))

Max Activating Token Index: 184

Text #18

Max Range: 0.3431. Min Range: -0.3431

Max Act: 0.2872. Min Act: -0.0001

Data Index: 863419 (C4 (Web Text))

Max Activating Token Index: 892

Text #19

Max Range: 0.3431. Min Range: -0.3431

Max Act: 0.2976. Min Act: -0.0001

Data Index: 643514 (C4 (Web Text))

Max Activating Token Index: 41