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

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

Neuron 1057 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4440. Min Range: -0.4440

Max Act: 0.4440. Min Act: -0.0001

Data Index: 1086232 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 0.4440. Min Range: -0.4440

Max Act: 0.4180. Min Act: -0.0001

Data Index: 1160348 (C4 (Web Text))

Max Activating Token Index: 27

Text #2

Max Range: 0.4440. Min Range: -0.4440

Max Act: 0.4140. Min Act: -0.0001

Data Index: 137994 (C4 (Web Text))

Max Activating Token Index: 457

Text #3

Max Range: 0.4440. Min Range: -0.4440

Max Act: 0.4215. Min Act: -0.0001

Data Index: 663143 (C4 (Web Text))

Max Activating Token Index: 520

Text #4

Max Range: 0.4440. Min Range: -0.4440

Max Act: 0.4233. Min Act: -0.0001

Data Index: 261022 (C4 (Web Text))

Max Activating Token Index: 947

Text #5

Max Range: 0.4440. Min Range: -0.4440

Max Act: 0.4283. Min Act: -0.0000

Data Index: 1058461 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 0.4440. Min Range: -0.4440

Max Act: 0.4032. Min Act: -0.0001

Data Index: 736887 (C4 (Web Text))

Max Activating Token Index: 115

Text #7

Max Range: 0.4440. Min Range: -0.4440

Max Act: 0.3977. Min Act: -0.0001

Data Index: 23662 (C4 (Web Text))

Max Activating Token Index: 957

Text #8

Max Range: 0.4440. Min Range: -0.4440

Max Act: 0.4049. Min Act: -0.0001

Data Index: 1074599 (C4 (Web Text))

Max Activating Token Index: 982

Text #9

Max Range: 0.4440. Min Range: -0.4440

Max Act: 0.3972. Min Act: -0.0001

Data Index: 866667 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 0.4440. Min Range: -0.4440

Max Act: 0.3895. Min Act: -0.0001

Data Index: 967257 (C4 (Web Text))

Max Activating Token Index: 805

Text #11

Max Range: 0.4440. Min Range: -0.4440

Max Act: 0.3769. Min Act: -0.0001

Data Index: 513850 (C4 (Web Text))

Max Activating Token Index: 620

Text #12

Max Range: 0.4440. Min Range: -0.4440

Max Act: 0.3850. Min Act: -0.0001

Data Index: 633782 (C4 (Web Text))

Max Activating Token Index: 360

Text #13

Max Range: 0.4440. Min Range: -0.4440

Max Act: 0.4089. Min Act: -0.0001

Data Index: 1128489 (C4 (Web Text))

Max Activating Token Index: 209

Text #14

Max Range: 0.4440. Min Range: -0.4440

Max Act: 0.3581. Min Act: -0.0001

Data Index: 906862 (C4 (Web Text))

Max Activating Token Index: 91

Text #15

Max Range: 0.4440. Min Range: -0.4440

Max Act: 0.3837. Min Act: -0.0001

Data Index: 85737 (C4 (Web Text))

Max Activating Token Index: 493

Text #16

Max Range: 0.4440. Min Range: -0.4440

Max Act: 0.3883. Min Act: -0.0001

Data Index: 82995 (C4 (Web Text))

Max Activating Token Index: 332

Text #17

Max Range: 0.4440. Min Range: -0.4440

Max Act: 0.3835. Min Act: -0.0001

Data Index: 1034840 (C4 (Web Text))

Max Activating Token Index: 783

Text #18

Max Range: 0.4440. Min Range: -0.4440

Max Act: 0.3942. Min Act: -0.0001

Data Index: 997901 (C4 (Web Text))

Max Activating Token Index: 431

Text #19

Max Range: 0.4440. Min Range: -0.4440

Max Act: 0.4053. Min Act: -0.0001

Data Index: 300469 (C4 (Web Text))

Max Activating Token Index: 972