Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2442 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.8258. Min Range: -0.8258

Max Act: 0.8258. Min Act: -0.0001

Data Index: 1081213 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 0.8258. Min Range: -0.8258

Max Act: 0.8187. Min Act: -0.0001

Data Index: 954128 (C4 (Web Text))

Max Activating Token Index: 208

Text #2

Max Range: 0.8258. Min Range: -0.8258

Max Act: 0.8086. Min Act: -0.0001

Data Index: 60621 (C4 (Web Text))

Max Activating Token Index: 147

Text #3

Max Range: 0.8258. Min Range: -0.8258

Max Act: 0.8146. Min Act: -0.0001

Data Index: 81517 (C4 (Web Text))

Max Activating Token Index: 176

Text #4

Max Range: 0.8258. Min Range: -0.8258

Max Act: 0.8036. Min Act: -0.0001

Data Index: 1165096 (C4 (Web Text))

Max Activating Token Index: 75

Text #5

Max Range: 0.8258. Min Range: -0.8258

Max Act: 0.7851. Min Act: -0.0001

Data Index: 165936 (C4 (Web Text))

Max Activating Token Index: 200

Text #6

Max Range: 0.8258. Min Range: -0.8258

Max Act: 0.7897. Min Act: -0.0001

Data Index: 12390 (C4 (Web Text))

Max Activating Token Index: 498

Text #7

Max Range: 0.8258. Min Range: -0.8258

Max Act: 0.7803. Min Act: -0.0001

Data Index: 1180126 (C4 (Web Text))

Max Activating Token Index: 25

Text #8

Max Range: 0.8258. Min Range: -0.8258

Max Act: 0.7656. Min Act: -0.0001

Data Index: 612988 (C4 (Web Text))

Max Activating Token Index: 173

Text #9

Max Range: 0.8258. Min Range: -0.8258

Max Act: 0.7712. Min Act: -0.0001

Data Index: 616444 (C4 (Web Text))

Max Activating Token Index: 107

Text #10

Max Range: 0.8258. Min Range: -0.8258

Max Act: 0.7547. Min Act: -0.0001

Data Index: 908448 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 0.8258. Min Range: -0.8258

Max Act: 0.7567. Min Act: -0.0001

Data Index: 762918 (C4 (Web Text))

Max Activating Token Index: 168

Text #12

Max Range: 0.8258. Min Range: -0.8258

Max Act: 0.7322. Min Act: -0.0001

Data Index: 1056530 (C4 (Web Text))

Max Activating Token Index: 26

Text #13

Max Range: 0.8258. Min Range: -0.8258

Max Act: 0.7455. Min Act: -0.0001

Data Index: 616716 (C4 (Web Text))

Max Activating Token Index: 151

Text #14

Max Range: 0.8258. Min Range: -0.8258

Max Act: 0.7389. Min Act: -0.0001

Data Index: 240531 (C4 (Web Text))

Max Activating Token Index: 95

Text #15

Max Range: 0.8258. Min Range: -0.8258

Max Act: 0.7394. Min Act: -0.0002

Data Index: 99301 (C4 (Web Text))

Max Activating Token Index: 601

Text #16

Max Range: 0.8258. Min Range: -0.8258

Max Act: 0.7377. Min Act: -0.0001

Data Index: 1165290 (C4 (Web Text))

Max Activating Token Index: 41

Text #17

Max Range: 0.8258. Min Range: -0.8258

Max Act: 0.7453. Min Act: -0.0001

Data Index: 286987 (C4 (Web Text))

Max Activating Token Index: 104

Text #18

Max Range: 0.8258. Min Range: -0.8258

Max Act: 0.7299. Min Act: -0.0001

Data Index: 42277 (C4 (Web Text))

Max Activating Token Index: 195

Text #19

Max Range: 0.8258. Min Range: -0.8258

Max Act: 0.7285. Min Act: -0.0001

Data Index: 475581 (C4 (Web Text))

Max Activating Token Index: 43