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

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

Neuron 3200 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2163. Min Range: -2.2163

Max Act: 2.2163. Min Act: -0.0000

Data Index: 1004424 (C4 (Web Text))

Max Activating Token Index: 80

Text #1

Max Range: 2.2163. Min Range: -2.2163

Max Act: 1.9682. Min Act: -0.0000

Data Index: 332572 (C4 (Web Text))

Max Activating Token Index: 454

Text #2

Max Range: 2.2163. Min Range: -2.2163

Max Act: 1.7752. Min Act: -0.0000

Data Index: 1030377 (C4 (Web Text))

Max Activating Token Index: 915

Text #3

Max Range: 2.2163. Min Range: -2.2163

Max Act: 1.7653. Min Act: -0.0000

Data Index: 580839 (C4 (Web Text))

Max Activating Token Index: 747

Text #4

Max Range: 2.2163. Min Range: -2.2163

Max Act: 1.6130. Min Act: -0.0000

Data Index: 976154 (C4 (Web Text))

Max Activating Token Index: 142

Text #5

Max Range: 2.2163. Min Range: -2.2163

Max Act: 1.6005. Min Act: -0.0000

Data Index: 548926 (C4 (Web Text))

Max Activating Token Index: 399

Text #6

Max Range: 2.2163. Min Range: -2.2163

Max Act: 1.4198. Min Act: -0.0000

Data Index: 596447 (C4 (Web Text))

Max Activating Token Index: 853

Text #7

Max Range: 2.2163. Min Range: -2.2163

Max Act: 1.4598. Min Act: -0.0000

Data Index: 238439 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 2.2163. Min Range: -2.2163

Max Act: 1.5275. Min Act: -0.0000

Data Index: 1016576 (C4 (Web Text))

Max Activating Token Index: 365

Text #9

Max Range: 2.2163. Min Range: -2.2163

Max Act: 1.5162. Min Act: -0.0000

Data Index: 173232 (C4 (Web Text))

Max Activating Token Index: 801

Text #10

Max Range: 2.2163. Min Range: -2.2163

Max Act: 1.4196. Min Act: -0.0000

Data Index: 702651 (C4 (Web Text))

Max Activating Token Index: 908

Text #11

Max Range: 2.2163. Min Range: -2.2163

Max Act: 1.3156. Min Act: -0.0000

Data Index: 758289 (C4 (Web Text))

Max Activating Token Index: 724

Text #12

Max Range: 2.2163. Min Range: -2.2163

Max Act: 1.3775. Min Act: -0.0000

Data Index: 439262 (C4 (Web Text))

Max Activating Token Index: 958

Text #13

Max Range: 2.2163. Min Range: -2.2163

Max Act: 1.4194. Min Act: -0.0000

Data Index: 1197814 (C4 (Web Text))

Max Activating Token Index: 51

Text #14

Max Range: 2.2163. Min Range: -2.2163

Max Act: 1.3241. Min Act: -0.0000

Data Index: 185235 (C4 (Web Text))

Max Activating Token Index: 982

Text #15

Max Range: 2.2163. Min Range: -2.2163

Max Act: 1.2465. Min Act: -0.0000

Data Index: 375232 (C4 (Web Text))

Max Activating Token Index: 494

Text #16

Max Range: 2.2163. Min Range: -2.2163

Max Act: 1.3146. Min Act: -0.0000

Data Index: 361091 (C4 (Web Text))

Max Activating Token Index: 523

Text #17

Max Range: 2.2163. Min Range: -2.2163

Max Act: 1.2139. Min Act: -0.0000

Data Index: 223192 (C4 (Web Text))

Max Activating Token Index: 799

Text #18

Max Range: 2.2163. Min Range: -2.2163

Max Act: 1.2116. Min Act: -0.0000

Data Index: 1031951 (C4 (Web Text))

Max Activating Token Index: 326

Text #19

Max Range: 2.2163. Min Range: -2.2163

Max Act: 1.2079. Min Act: -0.0000

Data Index: 773196 (C4 (Web Text))

Max Activating Token Index: 960