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

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

Neuron 2185 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.3552. Min Act: -0.0000

Data Index: 164105 (C4 (Web Text))

Max Activating Token Index: 929

Text #1

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.3422. Min Act: -0.0001

Data Index: 991502 (C4 (Web Text))

Max Activating Token Index: 97

Text #2

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.3263. Min Act: -0.0000

Data Index: 633603 (C4 (Web Text))

Max Activating Token Index: 12

Text #3

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.3384. Min Act: -0.0001

Data Index: 127260 (C4 (Web Text))

Max Activating Token Index: 983

Text #4

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.3141. Min Act: -0.0000

Data Index: 1229598 (C4 (Web Text))

Max Activating Token Index: 19

Text #5

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.3235. Min Act: 0.0001

Data Index: 1150277 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.3228. Min Act: -0.0000

Data Index: 507874 (C4 (Web Text))

Max Activating Token Index: 147

Text #7

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.3114. Min Act: -0.0000

Data Index: 1016987 (C4 (Web Text))

Max Activating Token Index: 93

Text #8

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.3177. Min Act: -0.0001

Data Index: 362606 (C4 (Web Text))

Max Activating Token Index: 55

Text #9

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.3122. Min Act: -0.0000

Data Index: 628453 (C4 (Web Text))

Max Activating Token Index: 1021

Text #10

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.3125. Min Act: -0.0000

Data Index: 820968 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.3017. Min Act: -0.0000

Data Index: 1085949 (C4 (Web Text))

Max Activating Token Index: 75

Text #12

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.3093. Min Act: -0.0000

Data Index: 1014506 (C4 (Web Text))

Max Activating Token Index: 259

Text #13

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.3083. Min Act: -0.0000

Data Index: 184048 (C4 (Web Text))

Max Activating Token Index: 106

Text #14

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.3060. Min Act: -0.0000

Data Index: 712880 (C4 (Web Text))

Max Activating Token Index: 160

Text #15

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2955. Min Act: 0.0000

Data Index: 1306756 (C4 (Web Text))

Max Activating Token Index: 51

Text #16

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.3150. Min Act: 0.0000

Data Index: 952123 (C4 (Web Text))

Max Activating Token Index: 102

Text #17

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.3049. Min Act: -0.0000

Data Index: 850469 (C4 (Web Text))

Max Activating Token Index: 706

Text #18

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2988. Min Act: 0.0001

Data Index: 852060 (C4 (Web Text))

Max Activating Token Index: 138

Text #19

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2848. Min Act: 0.0000

Data Index: 1226241 (C4 (Web Text))

Max Activating Token Index: 157