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

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

Neuron 1595 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2129. Min Range: -1.2129

Max Act: 1.2129. Min Act: -0.0000

Data Index: 1131434 (C4 (Web Text))

Max Activating Token Index: 297

Text #1

Max Range: 1.2129. Min Range: -1.2129

Max Act: 1.0890. Min Act: -0.0000

Data Index: 770020 (C4 (Web Text))

Max Activating Token Index: 411

Text #2

Max Range: 1.2129. Min Range: -1.2129

Max Act: 1.0259. Min Act: -0.0000

Data Index: 395527 (C4 (Web Text))

Max Activating Token Index: 718

Text #3

Max Range: 1.2129. Min Range: -1.2129

Max Act: 0.9636. Min Act: -0.0000

Data Index: 165368 (C4 (Web Text))

Max Activating Token Index: 391

Text #4

Max Range: 1.2129. Min Range: -1.2129

Max Act: 0.9702. Min Act: -0.0000

Data Index: 859471 (C4 (Web Text))

Max Activating Token Index: 20

Text #5

Max Range: 1.2129. Min Range: -1.2129

Max Act: 0.9044. Min Act: -0.0000

Data Index: 1427171 (Python Code)

Max Activating Token Index: 514

Text #6

Max Range: 1.2129. Min Range: -1.2129

Max Act: 0.9088. Min Act: -0.0000

Data Index: 1327127 (C4 (Web Text))

Max Activating Token Index: 138

Text #7

Max Range: 1.2129. Min Range: -1.2129

Max Act: 0.8496. Min Act: -0.0000

Data Index: 1080665 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 1.2129. Min Range: -1.2129

Max Act: 0.8302. Min Act: -0.0000

Data Index: 1145129 (C4 (Web Text))

Max Activating Token Index: 882

Text #9

Max Range: 1.2129. Min Range: -1.2129

Max Act: 0.7976. Min Act: -0.0000

Data Index: 1209945 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 1.2129. Min Range: -1.2129

Max Act: 0.8267. Min Act: -0.0000

Data Index: 1526160 (Python Code)

Max Activating Token Index: 134

Text #11

Max Range: 1.2129. Min Range: -1.2129

Max Act: 0.8091. Min Act: -0.0000

Data Index: 1291647 (C4 (Web Text))

Max Activating Token Index: 88

Text #12

Max Range: 1.2129. Min Range: -1.2129

Max Act: 0.7617. Min Act: -0.0000

Data Index: 763184 (C4 (Web Text))

Max Activating Token Index: 196

Text #13

Max Range: 1.2129. Min Range: -1.2129

Max Act: 0.7761. Min Act: -0.0000

Data Index: 312314 (C4 (Web Text))

Max Activating Token Index: 68

Text #14

Max Range: 1.2129. Min Range: -1.2129

Max Act: 0.7963. Min Act: -0.0000

Data Index: 365171 (C4 (Web Text))

Max Activating Token Index: 165

Text #15

Max Range: 1.2129. Min Range: -1.2129

Max Act: 0.7178. Min Act: -0.0000

Data Index: 1445944 (Python Code)

Max Activating Token Index: 457

Text #16

Max Range: 1.2129. Min Range: -1.2129

Max Act: 0.7226. Min Act: -0.0000

Data Index: 42356 (C4 (Web Text))

Max Activating Token Index: 203

Text #17

Max Range: 1.2129. Min Range: -1.2129

Max Act: 0.7337. Min Act: -0.0000

Data Index: 304401 (C4 (Web Text))

Max Activating Token Index: 492

Text #18

Max Range: 1.2129. Min Range: -1.2129

Max Act: 0.7188. Min Act: -0.0000

Data Index: 1405845 (Python Code)

Max Activating Token Index: 341

Text #19

Max Range: 1.2129. Min Range: -1.2129

Max Act: 0.7143. Min Act: -0.0000

Data Index: 365240 (C4 (Web Text))

Max Activating Token Index: 349