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

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

Neuron 1939 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4199. Min Range: -0.4199

Max Act: 0.4199. Min Act: -0.0000

Data Index: 71097 (C4 (Web Text))

Max Activating Token Index: 380

Text #1

Max Range: 0.4199. Min Range: -0.4199

Max Act: 0.3831. Min Act: -0.0000

Data Index: 1434965 (Python Code)

Max Activating Token Index: 186

Text #2

Max Range: 0.4199. Min Range: -0.4199

Max Act: 0.3764. Min Act: -0.0000

Data Index: 390701 (C4 (Web Text))

Max Activating Token Index: 925

Text #3

Max Range: 0.4199. Min Range: -0.4199

Max Act: 0.3304. Min Act: -0.0000

Data Index: 1140370 (C4 (Web Text))

Max Activating Token Index: 692

Text #4

Max Range: 0.4199. Min Range: -0.4199

Max Act: 0.3430. Min Act: -0.0000

Data Index: 1541493 (Python Code)

Max Activating Token Index: 81

Text #5

Max Range: 0.4199. Min Range: -0.4199

Max Act: 0.3486. Min Act: -0.0000

Data Index: 1292906 (C4 (Web Text))

Max Activating Token Index: 883

Text #6

Max Range: 0.4199. Min Range: -0.4199

Max Act: 0.3439. Min Act: -0.0000

Data Index: 1370244 (Python Code)

Max Activating Token Index: 530

Text #7

Max Range: 0.4199. Min Range: -0.4199

Max Act: 0.3470. Min Act: -0.0000

Data Index: 476119 (C4 (Web Text))

Max Activating Token Index: 954

Text #8

Max Range: 0.4199. Min Range: -0.4199

Max Act: 0.3330. Min Act: -0.0000

Data Index: 734779 (C4 (Web Text))

Max Activating Token Index: 943

Text #9

Max Range: 0.4199. Min Range: -0.4199

Max Act: 0.3079. Min Act: -0.0000

Data Index: 213305 (C4 (Web Text))

Max Activating Token Index: 963

Text #10

Max Range: 0.4199. Min Range: -0.4199

Max Act: 0.3174. Min Act: -0.0000

Data Index: 316426 (C4 (Web Text))

Max Activating Token Index: 157

Text #11

Max Range: 0.4199. Min Range: -0.4199

Max Act: 0.3074. Min Act: -0.0000

Data Index: 182067 (C4 (Web Text))

Max Activating Token Index: 801

Text #12

Max Range: 0.4199. Min Range: -0.4199

Max Act: 0.3150. Min Act: -0.0000

Data Index: 244358 (C4 (Web Text))

Max Activating Token Index: 792

Text #13

Max Range: 0.4199. Min Range: -0.4199

Max Act: 0.3154. Min Act: -0.0000

Data Index: 31678 (C4 (Web Text))

Max Activating Token Index: 1008

Text #14

Max Range: 0.4199. Min Range: -0.4199

Max Act: 0.3021. Min Act: -0.0000

Data Index: 234548 (C4 (Web Text))

Max Activating Token Index: 838

Text #15

Max Range: 0.4199. Min Range: -0.4199

Max Act: 0.3217. Min Act: -0.0000

Data Index: 1495052 (Python Code)

Max Activating Token Index: 707

Text #16

Max Range: 0.4199. Min Range: -0.4199

Max Act: 0.3291. Min Act: -0.0000

Data Index: 1348305 (C4 (Web Text))

Max Activating Token Index: 236

Text #17

Max Range: 0.4199. Min Range: -0.4199

Max Act: 0.3185. Min Act: -0.0000

Data Index: 350310 (C4 (Web Text))

Max Activating Token Index: 944

Text #18

Max Range: 0.4199. Min Range: -0.4199

Max Act: 0.2980. Min Act: -0.0000

Data Index: 1094357 (C4 (Web Text))

Max Activating Token Index: 761

Text #19

Max Range: 0.4199. Min Range: -0.4199

Max Act: 0.3126. Min Act: -0.0000

Data Index: 249380 (C4 (Web Text))

Max Activating Token Index: 105