Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5470 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.8208. Min Range: -1.8208

Max Act: 1.8208. Min Act: -0.0000

Data Index: 185088 (C4 (Web Text))

Max Activating Token Index: 222

Text #1

Max Range: 1.8208. Min Range: -1.8208

Max Act: 1.8137. Min Act: -0.0000

Data Index: 391918 (C4 (Web Text))

Max Activating Token Index: 974

Text #2

Max Range: 1.8208. Min Range: -1.8208

Max Act: 1.5524. Min Act: -0.0000

Data Index: 695659 (C4 (Web Text))

Max Activating Token Index: 845

Text #3

Max Range: 1.8208. Min Range: -1.8208

Max Act: 1.4904. Min Act: -0.0000

Data Index: 1273154 (C4 (Web Text))

Max Activating Token Index: 254

Text #4

Max Range: 1.8208. Min Range: -1.8208

Max Act: 1.4293. Min Act: -0.0000

Data Index: 762136 (C4 (Web Text))

Max Activating Token Index: 503

Text #5

Max Range: 1.8208. Min Range: -1.8208

Max Act: 1.3574. Min Act: -0.0000

Data Index: 1007149 (C4 (Web Text))

Max Activating Token Index: 690

Text #6

Max Range: 1.8208. Min Range: -1.8208

Max Act: 1.4247. Min Act: -0.0000

Data Index: 1232071 (C4 (Web Text))

Max Activating Token Index: 417

Text #7

Max Range: 1.8208. Min Range: -1.8208

Max Act: 1.2555. Min Act: -0.0000

Data Index: 723343 (C4 (Web Text))

Max Activating Token Index: 847

Text #8

Max Range: 1.8208. Min Range: -1.8208

Max Act: 1.3748. Min Act: -0.0000

Data Index: 175171 (C4 (Web Text))

Max Activating Token Index: 556

Text #9

Max Range: 1.8208. Min Range: -1.8208

Max Act: 1.2533. Min Act: -0.0000

Data Index: 1271260 (C4 (Web Text))

Max Activating Token Index: 261

Text #10

Max Range: 1.8208. Min Range: -1.8208

Max Act: 1.2153. Min Act: -0.0000

Data Index: 196075 (C4 (Web Text))

Max Activating Token Index: 621

Text #11

Max Range: 1.8208. Min Range: -1.8208

Max Act: 1.1992. Min Act: -0.0000

Data Index: 279800 (C4 (Web Text))

Max Activating Token Index: 856

Text #12

Max Range: 1.8208. Min Range: -1.8208

Max Act: 1.1571. Min Act: -0.0000

Data Index: 788671 (C4 (Web Text))

Max Activating Token Index: 423

Text #13

Max Range: 1.8208. Min Range: -1.8208

Max Act: 1.1176. Min Act: -0.0000

Data Index: 1100873 (C4 (Web Text))

Max Activating Token Index: 592

Text #14

Max Range: 1.8208. Min Range: -1.8208

Max Act: 1.1175. Min Act: -0.0000

Data Index: 1332618 (C4 (Web Text))

Max Activating Token Index: 515

Text #15

Max Range: 1.8208. Min Range: -1.8208

Max Act: 1.0429. Min Act: -0.0000

Data Index: 151087 (C4 (Web Text))

Max Activating Token Index: 612

Text #16

Max Range: 1.8208. Min Range: -1.8208

Max Act: 0.9896. Min Act: -0.0000

Data Index: 232071 (C4 (Web Text))

Max Activating Token Index: 691

Text #17

Max Range: 1.8208. Min Range: -1.8208

Max Act: 1.1023. Min Act: -0.0000

Data Index: 111249 (C4 (Web Text))

Max Activating Token Index: 459

Text #18

Max Range: 1.8208. Min Range: -1.8208

Max Act: 1.0335. Min Act: -0.0000

Data Index: 783123 (C4 (Web Text))

Max Activating Token Index: 843

Text #19

Max Range: 1.8208. Min Range: -1.8208

Max Act: 1.0796. Min Act: -0.0000

Data Index: 957222 (C4 (Web Text))

Max Activating Token Index: 903