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

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

Neuron 862 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: 1.8161. Min Range: -1.8161

Max Act: 1.8161. Min Act: -0.0001

Data Index: 1176618 (C4 (Web Text))

Max Activating Token Index: 795

Text #1

Max Range: 1.8161. Min Range: -1.8161

Max Act: 1.4351. Min Act: -0.0001

Data Index: 183236 (C4 (Web Text))

Max Activating Token Index: 676

Text #2

Max Range: 1.8161. Min Range: -1.8161

Max Act: 1.4326. Min Act: -0.0001

Data Index: 975067 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 1.8161. Min Range: -1.8161

Max Act: 1.3101. Min Act: -0.0001

Data Index: 722839 (C4 (Web Text))

Max Activating Token Index: 945

Text #4

Max Range: 1.8161. Min Range: -1.8161

Max Act: 1.3869. Min Act: -0.0001

Data Index: 69230 (C4 (Web Text))

Max Activating Token Index: 376

Text #5

Max Range: 1.8161. Min Range: -1.8161

Max Act: 1.4788. Min Act: -0.0001

Data Index: 1114432 (C4 (Web Text))

Max Activating Token Index: 536

Text #6

Max Range: 1.8161. Min Range: -1.8161

Max Act: 1.3469. Min Act: -0.0001

Data Index: 1320094 (C4 (Web Text))

Max Activating Token Index: 118

Text #7

Max Range: 1.8161. Min Range: -1.8161

Max Act: 1.4134. Min Act: -0.0001

Data Index: 863676 (C4 (Web Text))

Max Activating Token Index: 63

Text #8

Max Range: 1.8161. Min Range: -1.8161

Max Act: 1.3179. Min Act: -0.0001

Data Index: 1212562 (C4 (Web Text))

Max Activating Token Index: 209

Text #9

Max Range: 1.8161. Min Range: -1.8161

Max Act: 1.2199. Min Act: -0.0001

Data Index: 362659 (C4 (Web Text))

Max Activating Token Index: 223

Text #10

Max Range: 1.8161. Min Range: -1.8161

Max Act: 1.3244. Min Act: -0.0001

Data Index: 1056722 (C4 (Web Text))

Max Activating Token Index: 811

Text #11

Max Range: 1.8161. Min Range: -1.8161

Max Act: 1.2721. Min Act: -0.0001

Data Index: 789567 (C4 (Web Text))

Max Activating Token Index: 497

Text #12

Max Range: 1.8161. Min Range: -1.8161

Max Act: 1.1318. Min Act: -0.0001

Data Index: 731868 (C4 (Web Text))

Max Activating Token Index: 597

Text #13

Max Range: 1.8161. Min Range: -1.8161

Max Act: 1.2111. Min Act: -0.0001

Data Index: 1005142 (C4 (Web Text))

Max Activating Token Index: 905

Text #14

Max Range: 1.8161. Min Range: -1.8161

Max Act: 1.2459. Min Act: -0.0001

Data Index: 383063 (C4 (Web Text))

Max Activating Token Index: 370

Text #15

Max Range: 1.8161. Min Range: -1.8161

Max Act: 1.2973. Min Act: -0.0001

Data Index: 1100800 (C4 (Web Text))

Max Activating Token Index: 348

Text #16

Max Range: 1.8161. Min Range: -1.8161

Max Act: 1.1818. Min Act: -0.0001

Data Index: 587225 (C4 (Web Text))

Max Activating Token Index: 757

Text #17

Max Range: 1.8161. Min Range: -1.8161

Max Act: 1.1969. Min Act: -0.0001

Data Index: 669238 (C4 (Web Text))

Max Activating Token Index: 517

Text #18

Max Range: 1.8161. Min Range: -1.8161

Max Act: 1.1782. Min Act: -0.0001

Data Index: 1025440 (C4 (Web Text))

Max Activating Token Index: 330

Text #19

Max Range: 1.8161. Min Range: -1.8161

Max Act: 1.1335. Min Act: -0.0001

Data Index: 361295 (C4 (Web Text))

Max Activating Token Index: 89