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

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

Neuron 1475 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.2483. Min Act: -0.0001

Data Index: 883150 (C4 (Web Text))

Max Activating Token Index: 499

Text #1

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.2495. Min Act: -0.0001

Data Index: 185734 (C4 (Web Text))

Max Activating Token Index: 295

Text #2

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.2480. Min Act: -0.0001

Data Index: 1070936 (C4 (Web Text))

Max Activating Token Index: 17

Text #3

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.2279. Min Act: -0.0001

Data Index: 565585 (C4 (Web Text))

Max Activating Token Index: 424

Text #4

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.2229. Min Act: -0.0001

Data Index: 1244242 (C4 (Web Text))

Max Activating Token Index: 375

Text #5

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.2282. Min Act: -0.0001

Data Index: 1252143 (C4 (Web Text))

Max Activating Token Index: 458

Text #6

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.2133. Min Act: -0.0001

Data Index: 1118782 (C4 (Web Text))

Max Activating Token Index: 136

Text #7

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.2292. Min Act: -0.0001

Data Index: 200365 (C4 (Web Text))

Max Activating Token Index: 70

Text #8

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.2106. Min Act: -0.0001

Data Index: 1154066 (C4 (Web Text))

Max Activating Token Index: 851

Text #9

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.2179. Min Act: -0.0001

Data Index: 555611 (C4 (Web Text))

Max Activating Token Index: 181

Text #10

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.2154. Min Act: -0.0001

Data Index: 1206285 (C4 (Web Text))

Max Activating Token Index: 466

Text #11

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.2120. Min Act: -0.0001

Data Index: 672216 (C4 (Web Text))

Max Activating Token Index: 573

Text #12

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.2175. Min Act: -0.0001

Data Index: 4223 (C4 (Web Text))

Max Activating Token Index: 421

Text #13

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.2046. Min Act: -0.0001

Data Index: 1167570 (C4 (Web Text))

Max Activating Token Index: 785

Text #14

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.2117. Min Act: -0.0001

Data Index: 594336 (C4 (Web Text))

Max Activating Token Index: 515

Text #15

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.2093. Min Act: -0.0001

Data Index: 1036066 (C4 (Web Text))

Max Activating Token Index: 513

Text #16

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.2093. Min Act: -0.0000

Data Index: 1146495 (C4 (Web Text))

Max Activating Token Index: 153

Text #17

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.2089. Min Act: -0.0000

Data Index: 469959 (C4 (Web Text))

Max Activating Token Index: 782

Text #18

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.2093. Min Act: -0.0001

Data Index: 546939 (C4 (Web Text))

Max Activating Token Index: 743

Text #19

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.2083. Min Act: -0.0001

Data Index: 1124338 (C4 (Web Text))

Max Activating Token Index: 316