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

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

Neuron 25 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: 0.3402. Min Range: -0.3402

Max Act: 0.3402. Min Act: -0.0001

Data Index: 400196 (C4 (Web Text))

Max Activating Token Index: 638

Text #1

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.3170. Min Act: -0.0001

Data Index: 24920 (C4 (Web Text))

Max Activating Token Index: 1009

Text #2

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.3083. Min Act: -0.0001

Data Index: 406044 (C4 (Web Text))

Max Activating Token Index: 646

Text #3

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.3040. Min Act: -0.0001

Data Index: 148800 (C4 (Web Text))

Max Activating Token Index: 110

Text #4

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.3165. Min Act: -0.0001

Data Index: 1136067 (C4 (Web Text))

Max Activating Token Index: 442

Text #5

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.2933. Min Act: -0.0001

Data Index: 1188639 (C4 (Web Text))

Max Activating Token Index: 30

Text #6

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.2906. Min Act: -0.0001

Data Index: 28685 (C4 (Web Text))

Max Activating Token Index: 417

Text #7

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.3017. Min Act: -0.0001

Data Index: 1279674 (C4 (Web Text))

Max Activating Token Index: 924

Text #8

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.3091. Min Act: -0.0001

Data Index: 635097 (C4 (Web Text))

Max Activating Token Index: 1019

Text #9

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.2956. Min Act: -0.0001

Data Index: 62528 (C4 (Web Text))

Max Activating Token Index: 124

Text #10

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.2930. Min Act: -0.0001

Data Index: 248099 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.2934. Min Act: -0.0001

Data Index: 805195 (C4 (Web Text))

Max Activating Token Index: 67

Text #12

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.2853. Min Act: -0.0001

Data Index: 296408 (C4 (Web Text))

Max Activating Token Index: 650

Text #13

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.2958. Min Act: -0.0001

Data Index: 838473 (C4 (Web Text))

Max Activating Token Index: 222

Text #14

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.2872. Min Act: -0.0001

Data Index: 1197424 (C4 (Web Text))

Max Activating Token Index: 139

Text #15

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.2900. Min Act: -0.0001

Data Index: 61036 (C4 (Web Text))

Max Activating Token Index: 644

Text #16

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.2946. Min Act: -0.0001

Data Index: 1242472 (C4 (Web Text))

Max Activating Token Index: 981

Text #17

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.2822. Min Act: -0.0001

Data Index: 401013 (C4 (Web Text))

Max Activating Token Index: 578

Text #18

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.2754. Min Act: -0.0001

Data Index: 639039 (C4 (Web Text))

Max Activating Token Index: 297

Text #19

Max Range: 0.3402. Min Range: -0.3402

Max Act: 0.2766. Min Act: -0.0001

Data Index: 372884 (C4 (Web Text))

Max Activating Token Index: 993