Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4808 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0197. Min Act: -0.0001

Data Index: 1159199 (C4 (Web Text))

Max Activating Token Index: 972

Text #1

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0175. Min Act: -0.0001

Data Index: 980008 (C4 (Web Text))

Max Activating Token Index: 516

Text #2

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0171. Min Act: -0.0001

Data Index: 497061 (C4 (Web Text))

Max Activating Token Index: 180

Text #3

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0140. Min Act: -0.0001

Data Index: 274260 (C4 (Web Text))

Max Activating Token Index: 580

Text #4

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0132. Min Act: -0.0001

Data Index: 195683 (C4 (Web Text))

Max Activating Token Index: 203

Text #5

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0152. Min Act: -0.0001

Data Index: 363911 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0154. Min Act: -0.0001

Data Index: 874548 (C4 (Web Text))

Max Activating Token Index: 360

Text #7

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0160. Min Act: -0.0001

Data Index: 304313 (C4 (Web Text))

Max Activating Token Index: 764

Text #8

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0141. Min Act: -0.0001

Data Index: 602110 (C4 (Web Text))

Max Activating Token Index: 247

Text #9

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0151. Min Act: -0.0001

Data Index: 713500 (C4 (Web Text))

Max Activating Token Index: 889

Text #10

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0140. Min Act: -0.0001

Data Index: 429791 (C4 (Web Text))

Max Activating Token Index: 294

Text #11

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0140. Min Act: -0.0001

Data Index: 1197586 (C4 (Web Text))

Max Activating Token Index: 734

Text #12

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0138. Min Act: -0.0001

Data Index: 939941 (C4 (Web Text))

Max Activating Token Index: 419

Text #13

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0137. Min Act: -0.0001

Data Index: 43661 (C4 (Web Text))

Max Activating Token Index: 742

Text #14

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0134. Min Act: -0.0001

Data Index: 834518 (C4 (Web Text))

Max Activating Token Index: 148

Text #15

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0139. Min Act: -0.0001

Data Index: 1006722 (C4 (Web Text))

Max Activating Token Index: 875

Text #16

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0162. Min Act: -0.0001

Data Index: 410077 (C4 (Web Text))

Max Activating Token Index: 864

Text #17

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0139. Min Act: -0.0001

Data Index: 454575 (C4 (Web Text))

Max Activating Token Index: 34

Text #18

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0139. Min Act: -0.0001

Data Index: 1351832 (C4 (Web Text))

Max Activating Token Index: 4

Text #19

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0139. Min Act: -0.0001

Data Index: 1341392 (C4 (Web Text))

Max Activating Token Index: 4