Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 847 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.3605. Min Act: -0.0001

Data Index: 1123375 (C4 (Web Text))

Max Activating Token Index: 888

Text #1

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.3492. Min Act: -0.0001

Data Index: 202329 (C4 (Web Text))

Max Activating Token Index: 652

Text #2

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.3470. Min Act: -0.0001

Data Index: 1286207 (C4 (Web Text))

Max Activating Token Index: 530

Text #3

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.3372. Min Act: -0.0001

Data Index: 476295 (C4 (Web Text))

Max Activating Token Index: 38

Text #4

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.3349. Min Act: -0.0001

Data Index: 192987 (C4 (Web Text))

Max Activating Token Index: 572

Text #5

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.3015. Min Act: -0.0000

Data Index: 1293513 (C4 (Web Text))

Max Activating Token Index: 797

Text #6

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.3322. Min Act: -0.0001

Data Index: 935913 (C4 (Web Text))

Max Activating Token Index: 334

Text #7

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.3208. Min Act: -0.0001

Data Index: 1268409 (C4 (Web Text))

Max Activating Token Index: 668

Text #8

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.2971. Min Act: -0.0001

Data Index: 722808 (C4 (Web Text))

Max Activating Token Index: 797

Text #9

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.3030. Min Act: -0.0000

Data Index: 210953 (C4 (Web Text))

Max Activating Token Index: 793

Text #10

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.3093. Min Act: -0.0000

Data Index: 1205015 (C4 (Web Text))

Max Activating Token Index: 418

Text #11

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.3199. Min Act: -0.0001

Data Index: 956453 (C4 (Web Text))

Max Activating Token Index: 97

Text #12

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.2877. Min Act: -0.0001

Data Index: 946 (C4 (Web Text))

Max Activating Token Index: 143

Text #13

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.3147. Min Act: -0.0001

Data Index: 770164 (C4 (Web Text))

Max Activating Token Index: 180

Text #14

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.2752. Min Act: -0.0001

Data Index: 1237508 (C4 (Web Text))

Max Activating Token Index: 649

Text #15

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.3233. Min Act: -0.0000

Data Index: 1058891 (C4 (Web Text))

Max Activating Token Index: 825

Text #16

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.2985. Min Act: -0.0001

Data Index: 705301 (C4 (Web Text))

Max Activating Token Index: 506

Text #17

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.2919. Min Act: -0.0000

Data Index: 565855 (C4 (Web Text))

Max Activating Token Index: 782

Text #18

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.3161. Min Act: -0.0001

Data Index: 915028 (C4 (Web Text))

Max Activating Token Index: 805

Text #19

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.3220. Min Act: -0.0001

Data Index: 1015101 (C4 (Web Text))

Max Activating Token Index: 855