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

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

Neuron 1408 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4309. Min Range: -3.4309

Max Act: 3.4309. Min Act: -0.0001

Data Index: 941455 (C4 (Web Text))

Max Activating Token Index: 149

Text #1

Max Range: 3.4309. Min Range: -3.4309

Max Act: 3.2028. Min Act: -0.0001

Data Index: 148555 (C4 (Web Text))

Max Activating Token Index: 560

Text #2

Max Range: 3.4309. Min Range: -3.4309

Max Act: 3.1567. Min Act: -0.0001

Data Index: 456859 (C4 (Web Text))

Max Activating Token Index: 242

Text #3

Max Range: 3.4309. Min Range: -3.4309

Max Act: 3.2546. Min Act: -0.0001

Data Index: 695728 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 3.4309. Min Range: -3.4309

Max Act: 2.9341. Min Act: -0.0001

Data Index: 385274 (C4 (Web Text))

Max Activating Token Index: 286

Text #5

Max Range: 3.4309. Min Range: -3.4309

Max Act: 3.0623. Min Act: -0.0001

Data Index: 1333164 (C4 (Web Text))

Max Activating Token Index: 81

Text #6

Max Range: 3.4309. Min Range: -3.4309

Max Act: 2.8651. Min Act: -0.0001

Data Index: 782483 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 3.4309. Min Range: -3.4309

Max Act: 2.8367. Min Act: -0.0000

Data Index: 1016869 (C4 (Web Text))

Max Activating Token Index: 164

Text #8

Max Range: 3.4309. Min Range: -3.4309

Max Act: 2.7874. Min Act: -0.0001

Data Index: 163099 (C4 (Web Text))

Max Activating Token Index: 79

Text #9

Max Range: 3.4309. Min Range: -3.4309

Max Act: 2.7707. Min Act: -0.0001

Data Index: 781930 (C4 (Web Text))

Max Activating Token Index: 1010

Text #10

Max Range: 3.4309. Min Range: -3.4309

Max Act: 2.7048. Min Act: -0.0000

Data Index: 564260 (C4 (Web Text))

Max Activating Token Index: 581

Text #11

Max Range: 3.4309. Min Range: -3.4309

Max Act: 2.7075. Min Act: -0.0001

Data Index: 1341126 (C4 (Web Text))

Max Activating Token Index: 711

Text #12

Max Range: 3.4309. Min Range: -3.4309

Max Act: 2.6744. Min Act: -0.0001

Data Index: 278321 (C4 (Web Text))

Max Activating Token Index: 511

Text #13

Max Range: 3.4309. Min Range: -3.4309

Max Act: 2.5371. Min Act: -0.0001

Data Index: 773747 (C4 (Web Text))

Max Activating Token Index: 115

Text #14

Max Range: 3.4309. Min Range: -3.4309

Max Act: 2.5233. Min Act: -0.0001

Data Index: 1185837 (C4 (Web Text))

Max Activating Token Index: 121

Text #15

Max Range: 3.4309. Min Range: -3.4309

Max Act: 2.6550. Min Act: -0.0001

Data Index: 338148 (C4 (Web Text))

Max Activating Token Index: 169

Text #16

Max Range: 3.4309. Min Range: -3.4309

Max Act: 2.6033. Min Act: -0.0001

Data Index: 1040033 (C4 (Web Text))

Max Activating Token Index: 301

Text #17

Max Range: 3.4309. Min Range: -3.4309

Max Act: 2.4567. Min Act: -0.0001

Data Index: 764511 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 3.4309. Min Range: -3.4309

Max Act: 2.5778. Min Act: -0.0001

Data Index: 634285 (C4 (Web Text))

Max Activating Token Index: 91

Text #19

Max Range: 3.4309. Min Range: -3.4309

Max Act: 2.8262. Min Act: -0.0001

Data Index: 1150708 (C4 (Web Text))

Max Activating Token Index: 772