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

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

Neuron 841 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2303. Min Range: -0.2303

Max Act: 0.2301. Min Act: -0.0001

Data Index: 507721 (C4 (Web Text))

Max Activating Token Index: 439

Text #1

Max Range: 0.2303. Min Range: -0.2303

Max Act: 0.2278. Min Act: -0.0001

Data Index: 1221427 (C4 (Web Text))

Max Activating Token Index: 980

Text #2

Max Range: 0.2303. Min Range: -0.2303

Max Act: 0.2258. Min Act: -0.0001

Data Index: 707294 (C4 (Web Text))

Max Activating Token Index: 936

Text #3

Max Range: 0.2303. Min Range: -0.2303

Max Act: 0.2303. Min Act: -0.0001

Data Index: 877404 (C4 (Web Text))

Max Activating Token Index: 550

Text #4

Max Range: 0.2303. Min Range: -0.2303

Max Act: 0.2181. Min Act: -0.0001

Data Index: 1106592 (C4 (Web Text))

Max Activating Token Index: 168

Text #5

Max Range: 0.2303. Min Range: -0.2303

Max Act: 0.2124. Min Act: -0.0001

Data Index: 684681 (C4 (Web Text))

Max Activating Token Index: 815

Text #6

Max Range: 0.2303. Min Range: -0.2303

Max Act: 0.2152. Min Act: -0.0001

Data Index: 922948 (C4 (Web Text))

Max Activating Token Index: 111

Text #7

Max Range: 0.2303. Min Range: -0.2303

Max Act: 0.2093. Min Act: -0.0001

Data Index: 801772 (C4 (Web Text))

Max Activating Token Index: 72

Text #8

Max Range: 0.2303. Min Range: -0.2303

Max Act: 0.2134. Min Act: -0.0001

Data Index: 335960 (C4 (Web Text))

Max Activating Token Index: 219

Text #9

Max Range: 0.2303. Min Range: -0.2303

Max Act: 0.2115. Min Act: -0.0001

Data Index: 875253 (C4 (Web Text))

Max Activating Token Index: 968

Text #10

Max Range: 0.2303. Min Range: -0.2303

Max Act: 0.2089. Min Act: -0.0001

Data Index: 1356570 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 0.2303. Min Range: -0.2303

Max Act: 0.2090. Min Act: -0.0001

Data Index: 1306473 (C4 (Web Text))

Max Activating Token Index: 192

Text #12

Max Range: 0.2303. Min Range: -0.2303

Max Act: 0.2004. Min Act: -0.0001

Data Index: 1169354 (C4 (Web Text))

Max Activating Token Index: 14

Text #13

Max Range: 0.2303. Min Range: -0.2303

Max Act: 0.2062. Min Act: -0.0001

Data Index: 995187 (C4 (Web Text))

Max Activating Token Index: 722

Text #14

Max Range: 0.2303. Min Range: -0.2303

Max Act: 0.2054. Min Act: -0.0001

Data Index: 690715 (C4 (Web Text))

Max Activating Token Index: 57

Text #15

Max Range: 0.2303. Min Range: -0.2303

Max Act: 0.2045. Min Act: -0.0001

Data Index: 618102 (C4 (Web Text))

Max Activating Token Index: 545

Text #16

Max Range: 0.2303. Min Range: -0.2303

Max Act: 0.2103. Min Act: -0.0001

Data Index: 948779 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 0.2303. Min Range: -0.2303

Max Act: 0.1977. Min Act: -0.0001

Data Index: 1191818 (C4 (Web Text))

Max Activating Token Index: 76

Text #18

Max Range: 0.2303. Min Range: -0.2303

Max Act: 0.1951. Min Act: -0.0001

Data Index: 994112 (C4 (Web Text))

Max Activating Token Index: 969

Text #19

Max Range: 0.2303. Min Range: -0.2303

Max Act: 0.1952. Min Act: -0.0001

Data Index: 1276518 (C4 (Web Text))

Max Activating Token Index: 876