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

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

Neuron 1923 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.4683. Min Act: -0.0002

Data Index: 94638 (C4 (Web Text))

Max Activating Token Index: 982

Text #1

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3141. Min Act: -0.0002

Data Index: 973825 (C4 (Web Text))

Max Activating Token Index: 537

Text #2

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3290. Min Act: -0.0002

Data Index: 313615 (C4 (Web Text))

Max Activating Token Index: 922

Text #3

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3395. Min Act: -0.0002

Data Index: 817118 (C4 (Web Text))

Max Activating Token Index: 195

Text #4

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3384. Min Act: -0.0002

Data Index: 321150 (C4 (Web Text))

Max Activating Token Index: 315

Text #5

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.2634. Min Act: -0.0002

Data Index: 597487 (C4 (Web Text))

Max Activating Token Index: 706

Text #6

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3138. Min Act: -0.0002

Data Index: 380304 (C4 (Web Text))

Max Activating Token Index: 651

Text #7

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.2948. Min Act: -0.0002

Data Index: 143542 (C4 (Web Text))

Max Activating Token Index: 701

Text #8

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3369. Min Act: -0.0002

Data Index: 608609 (C4 (Web Text))

Max Activating Token Index: 409

Text #9

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3247. Min Act: -0.0002

Data Index: 1109307 (C4 (Web Text))

Max Activating Token Index: 949

Text #10

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3250. Min Act: -0.0002

Data Index: 488193 (C4 (Web Text))

Max Activating Token Index: 512

Text #11

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3085. Min Act: -0.0002

Data Index: 1233219 (C4 (Web Text))

Max Activating Token Index: 33

Text #12

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3240. Min Act: -0.0002

Data Index: 1272479 (C4 (Web Text))

Max Activating Token Index: 936

Text #13

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3346. Min Act: -0.0002

Data Index: 84416 (C4 (Web Text))

Max Activating Token Index: 48

Text #14

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3183. Min Act: -0.0002

Data Index: 643151 (C4 (Web Text))

Max Activating Token Index: 767

Text #15

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3315. Min Act: -0.0002

Data Index: 899007 (C4 (Web Text))

Max Activating Token Index: 519

Text #16

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3300. Min Act: -0.0002

Data Index: 668419 (C4 (Web Text))

Max Activating Token Index: 975

Text #17

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3093. Min Act: -0.0002

Data Index: 407167 (C4 (Web Text))

Max Activating Token Index: 98

Text #18

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.2889. Min Act: -0.0002

Data Index: 307517 (C4 (Web Text))

Max Activating Token Index: 937

Text #19

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3066. Min Act: -0.0002

Data Index: 1346460 (C4 (Web Text))

Max Activating Token Index: 40