Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1835 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0207. Min Act: -0.0004

Data Index: 348696 (C4 (Web Text))

Max Activating Token Index: 378

Text #1

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0148. Min Act: -0.0004

Data Index: 144782 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0171. Min Act: -0.0004

Data Index: 685492 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0132. Min Act: -0.0004

Data Index: 1093534 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0131. Min Act: -0.0004

Data Index: 1052313 (C4 (Web Text))

Max Activating Token Index: 578

Text #5

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0136. Min Act: -0.0004

Data Index: 1212835 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0138. Min Act: -0.0004

Data Index: 1584357 (Python Code)

Max Activating Token Index: 50

Text #7

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0135. Min Act: -0.0004

Data Index: 373683 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0141. Min Act: -0.0004

Data Index: 825402 (C4 (Web Text))

Max Activating Token Index: 573

Text #9

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0146. Min Act: -0.0004

Data Index: 153989 (C4 (Web Text))

Max Activating Token Index: 654

Text #10

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0133. Min Act: -0.0004

Data Index: 1485354 (Python Code)

Max Activating Token Index: 72

Text #11

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0120. Min Act: -0.0004

Data Index: 615888 (C4 (Web Text))

Max Activating Token Index: 544

Text #12

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0135. Min Act: -0.0004

Data Index: 1238115 (C4 (Web Text))

Max Activating Token Index: 447

Text #13

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0142. Min Act: -0.0004

Data Index: 663685 (C4 (Web Text))

Max Activating Token Index: 304

Text #14

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0131. Min Act: -0.0004

Data Index: 1426748 (Python Code)

Max Activating Token Index: 125

Text #15

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0125. Min Act: -0.0004

Data Index: 1398587 (Python Code)

Max Activating Token Index: 277

Text #16

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0121. Min Act: -0.0004

Data Index: 1393957 (Python Code)

Max Activating Token Index: 359

Text #17

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0147. Min Act: -0.0004

Data Index: 1651474 (Python Code)

Max Activating Token Index: 317

Text #18

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0122. Min Act: -0.0004

Data Index: 767596 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0132. Min Act: -0.0004

Data Index: 802685 (C4 (Web Text))

Max Activating Token Index: 674