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

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

Neuron 3234 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8161. Min Range: -3.8161

Max Act: 3.6658. Min Act: -0.0001

Data Index: 713485 (C4 (Web Text))

Max Activating Token Index: 536

Text #1

Max Range: 3.8161. Min Range: -3.8161

Max Act: 3.8161. Min Act: -0.0001

Data Index: 96631 (C4 (Web Text))

Max Activating Token Index: 131

Text #2

Max Range: 3.8161. Min Range: -3.8161

Max Act: 3.4937. Min Act: -0.0001

Data Index: 997660 (C4 (Web Text))

Max Activating Token Index: 524

Text #3

Max Range: 3.8161. Min Range: -3.8161

Max Act: 3.3397. Min Act: -0.0001

Data Index: 500542 (C4 (Web Text))

Max Activating Token Index: 121

Text #4

Max Range: 3.8161. Min Range: -3.8161

Max Act: 3.4337. Min Act: -0.0001

Data Index: 1127203 (C4 (Web Text))

Max Activating Token Index: 36

Text #5

Max Range: 3.8161. Min Range: -3.8161

Max Act: 3.3599. Min Act: -0.0001

Data Index: 39595 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 3.8161. Min Range: -3.8161

Max Act: 3.4440. Min Act: -0.0001

Data Index: 740498 (C4 (Web Text))

Max Activating Token Index: 859

Text #7

Max Range: 3.8161. Min Range: -3.8161

Max Act: 3.2586. Min Act: -0.0001

Data Index: 338928 (C4 (Web Text))

Max Activating Token Index: 37

Text #8

Max Range: 3.8161. Min Range: -3.8161

Max Act: 3.3794. Min Act: -0.0001

Data Index: 253848 (C4 (Web Text))

Max Activating Token Index: 70

Text #9

Max Range: 3.8161. Min Range: -3.8161

Max Act: 3.2184. Min Act: -0.0001

Data Index: 258184 (C4 (Web Text))

Max Activating Token Index: 378

Text #10

Max Range: 3.8161. Min Range: -3.8161

Max Act: 3.1677. Min Act: -0.0001

Data Index: 340388 (C4 (Web Text))

Max Activating Token Index: 328

Text #11

Max Range: 3.8161. Min Range: -3.8161

Max Act: 3.0206. Min Act: -0.0001

Data Index: 1237664 (C4 (Web Text))

Max Activating Token Index: 113

Text #12

Max Range: 3.8161. Min Range: -3.8161

Max Act: 2.9683. Min Act: -0.0001

Data Index: 96328 (C4 (Web Text))

Max Activating Token Index: 71

Text #13

Max Range: 3.8161. Min Range: -3.8161

Max Act: 2.6830. Min Act: -0.0001

Data Index: 1269401 (C4 (Web Text))

Max Activating Token Index: 729

Text #14

Max Range: 3.8161. Min Range: -3.8161

Max Act: 3.2168. Min Act: -0.0001

Data Index: 324951 (C4 (Web Text))

Max Activating Token Index: 675

Text #15

Max Range: 3.8161. Min Range: -3.8161

Max Act: 2.9182. Min Act: -0.0001

Data Index: 738155 (C4 (Web Text))

Max Activating Token Index: 246

Text #16

Max Range: 3.8161. Min Range: -3.8161

Max Act: 2.9160. Min Act: -0.0001

Data Index: 1131453 (C4 (Web Text))

Max Activating Token Index: 515

Text #17

Max Range: 3.8161. Min Range: -3.8161

Max Act: 3.0164. Min Act: -0.0000

Data Index: 1306800 (C4 (Web Text))

Max Activating Token Index: 994

Text #18

Max Range: 3.8161. Min Range: -3.8161

Max Act: 2.9590. Min Act: -0.0001

Data Index: 1216146 (C4 (Web Text))

Max Activating Token Index: 527

Text #19

Max Range: 3.8161. Min Range: -3.8161

Max Act: 2.9485. Min Act: -0.0001

Data Index: 1139538 (C4 (Web Text))

Max Activating Token Index: 757